{"updated_at":"2026-10-27T04:21:16+00:00","source":"Models.dev","source_url":"https://github.com/anomalyco/models.dev","source_digest":"13ab59bf50f6f3dd9161f808f76fc32ddcda77997a1be0a8382f0d419a05ce51","coverage_start":"2022-12-15","coverage_note":"A selection of model-level records from Models.dev across 11 labs. Release dates are community-maintained. Coverage varies by lab and year; counts describe this catalog, not every AI launch.","excluded":{"imprecise_date":9,"future_date":0,"alias":27},"labs":[{"id":"openai","name":"OpenAI","mark":"O","color":"#f5f5f5","news":"https://openai.com/news/"},{"id":"anthropic","name":"Anthropic","mark":"A","color":"#e8a886","news":"https://www.anthropic.com/news"},{"id":"google","name":"Google","mark":"G","color":"#8db9ff","news":"https://deepmind.google/blog/"},{"id":"meta","name":"Meta","mark":"M","color":"#899bff","news":"https://ai.meta.com/blog/"},{"id":"xai","name":"xAI","mark":"x","color":"#c7c9d1","news":"https://x.ai/news"},{"id":"deepseek","name":"DeepSeek","mark":"D","color":"#72b9e9","news":"https://api-docs.deepseek.com/"},{"id":"mistral","name":"Mistral","mark":"▥","color":"#f0bc67","news":"https://mistral.ai/news/"},{"id":"alibaba","name":"Qwen","mark":"Q","color":"#b6a0f0","news":"https://qwen.ai/research"},{"id":"moonshotai","name":"Moonshot AI","mark":"K","color":"#ddabd6","news":"https://www.kimi.ai/blog/"},{"id":"zhipuai","name":"Z.ai","mark":"Z","color":"#9dc9c3","news":"https://docs.z.ai/release-notes/new-released"},{"id":"nvidia","name":"NVIDIA","mark":"N","color":"#b2d77b","news":"https://blogs.nvidia.com/blog/category/generative-ai/"}],"models":[{"id":"openai/gpt-6.1-terra","name":"GPT-6.1 Terra","lab":"openai","date":"2026-10-26","description":"Fast, efficient model for visual reasoning, precise computer use, and clear, natural writing.","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6.1-terra.toml","kind":"model","articles":[{"title":"Introducing GPT-6.1 Terra","url":"https://openai.com/index/introducing-gpt-6-1-terra","date":"2026-10-26","published_at":"2026-10-26T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"moonshotai/kimi-k3.1-pro","name":"Kimi K3.1 Pro","lab":"moonshotai","date":"2026-10-23","description":"Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work","context":1048576,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k3.1-pro.toml","kind":"model","articles":[{"title":"Kimi K3.1 Pro Tech Blog: Advancing Open Intelligence","url":"https://www.kimi.ai/blog/kimi-k3-1-pro","date":null,"published_at":null,"primary":false,"publisher":"moonshotai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"mistral/voxtral-3","name":"Voxtral 3","lab":"mistral","date":"2026-10-20","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/voxtral-3/","kind":"model","articles":[{"title":"Voxtral 3: Voice Agent SDK & Speech Models in 50+ Languages","url":"https://mistral.ai/news/voxtral-3/","date":"2026-10-20","published_at":"2026-10-20T12:00:22+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"deepseek/deepseek-v4.1-flash-1017","name":"DeepSeek V4.1 Flash 1017","lab":"deepseek","date":"2026-10-17","description":"October 17 update of DeepSeek V4.1 Flash with improved reasoning, coding, agentic tasks, and visual understanding","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4.1-flash-1017.toml","kind":"model","articles":[{"title":"DeepSeek-V4.1-Flash-1017: Wish-Driven Programming Made Real","url":"https://api-docs.deepseek.com/news/news261017","date":"2026-10-17","published_at":"2026-10-17T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","lab":"nvidia","date":"2026-10-15","description":"NVIDIA vision-language reasoning model for text, image, and video understanding and agentic tool use","context":1048576,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-super-vl-120b-a12b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-3.5-super-120b-a12b","name":"Nemotron 3.5 Super 120B A12B","lab":"nvidia","date":"2026-10-15","description":"NVIDIA Nemotron 3.5 Super reasoning model (120B total, 12B active) served with text-only input","context":1048576,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-super-120b-a12b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/muse-spark-open","name":"Muse Spark Open","lab":"meta","date":"2026-10-15","description":"Muse Spark Open is an 816B total / 42B active open-weight multimodal reasoning model from Meta for coding and long-horizon agentic work, with 1M-token context.","context":1048576,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image","video","audio/wav","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-open.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-voice-3.0","name":"Grok Voice 3.0","lab":"xai","date":"2026-10-14","description":"Speech-to-speech model for real-time voice agents with tool use and optional reasoning","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","audio/opus"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","audio/opus"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-voice-3.0.toml","kind":"model","articles":[{"title":"Introducing Grok Voice 3.0","url":"https://x.ai/news/grok-voice-3","date":"2026-10-14","published_at":"2026-10-14T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"meta/muse-wonder-full","name":"Muse Wonder Full","lab":"meta","date":"2026-10-12","description":"Muse Wonder Full is the most capable model in Meta's Muse Wonder series, built for long-running professional agents and ultra-long-horizon software engineering. It shares Muse Wonder's Active Memory and Active Focus capabilities and generally scores higher on Meta's agentic and coding evaluations.","context":1048576,"output":null,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-wonder-full.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/muse-wonder-1.0","name":"Muse Wonder","lab":"meta","date":"2026-10-12","description":"Muse Wonder is a frontier multimodal reasoning model from Meta for personal and professional agents, long-horizon coding, and computer use. It combines Active Memory, which carries relevant context across conversations, with Active Focus, which keeps it working through blockers toward a goal.","context":1048576,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","video/mp4","application/pdf","audio/mpeg","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-wonder-1.0.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-image-2.1-turbo","name":"Qwen-Image-2.1-Turbo","lab":"alibaba","date":"2026-10-09","description":"8-step Qwen-Image-2.1 model for fast image generation and editing","context":null,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/tiff","image/webp","image/gif"],"output_modalities":["image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-image-2.1-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-haiku-5-5","name":"Claude Haiku 5.5","lab":"anthropic","date":"2026-10-07","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-haiku-5-5.toml","kind":"model","articles":[{"title":"Released Claude Haiku 5.5","url":"https://platform.claude.com/docs/en/release-notes/overview#october-7-2026","date":"2026-10-07","published_at":"2026-10-07T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-nano-banana-2.1","name":"Nano Banana 2.1","lab":"google","date":"2026-10-06","description":"Image model for prompt-driven generation, multi-turn editing, and visual design workflows","context":131072,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-nano-banana-2.1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-large-4","name":"Mistral Large 4","lab":"mistral","date":"2026-10-06","description":"Mistral's 1T-parameter multimodal MoE for reasoning, coding, and agentic work","context":1048576,"output":262144,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-4.toml","kind":"model","articles":[{"title":"Introducing Mistral Large 4 | Mistral","url":"https://mistral.ai/news/mistral-large-4/","date":"2026-10-06","published_at":"2026-10-06T12:00:27+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-image-2.1-pro","name":"Qwen-Image-2.1-Pro","lab":"alibaba","date":"2026-10-02","description":"Qwen-Image-2.1 API tier for image generation and editing with native transparency","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/tiff","image/webp","image/gif"],"output_modalities":["image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-image-2.1-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-imagine-video-1.5-lite","name":"Grok Imagine Video 1.5 Lite","lab":"xai","date":"2026-10-01","description":"Cost-efficient video model for text-to-video and image-to-video generation","context":1024,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-video-1.5-lite.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-4-argon","name":"Gemini 4 Argon","lab":"google","date":"2026-09-30","description":"Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-4-argon.toml","kind":"model","articles":[{"title":"Gemini 4 Argon: our next era of frontier intelligence","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-4-argon/","date":"2026-09-30","published_at":"2026-09-30T20:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/gemini-4-argon-our-next-era-of-frontier-intelligence/"]},{"title":"Gemini 4 Argon: Built to solve your hardest problems","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-4-argon/","date":"2026-10-13","published_at":"2026-10-13T16:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-4-argon/"]},{"title":"Gemini 4 Argon is now available for developers.","url":"https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-4-argon/","date":"2026-10-13","published_at":"2026-10-13T16:00:00+00:00","primary":true,"publisher":"google","also":[]},{"title":"Gemini 4 Argon comes to the Gemini app.","url":"https://blog.google/innovation-and-ai/products/gemini-app/gemini-4-argon-availability/","date":"2026-10-13","published_at":"2026-10-13T16:00:00+00:00","primary":false,"publisher":"google","also":[]},{"title":"Gemini 4 Argon for Robotics","url":"https://deepmind.google/blog/gemini-4-argon-for-robotics/","date":"2026-10-13","published_at":"2026-10-13T16:01:58+00:00","primary":false,"publisher":"google","also":[]},{"title":"See what 5 builders are making with Gemini 4 Argon","url":"https://blog.google/products-and-platforms/products/gemini/gemini-4-argon-builders/","date":"2026-10-23","published_at":"2026-10-23T16:00:00+00:00","primary":false,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-6.1-sol","name":"GPT-6.1 Sol","lab":"openai","date":"2026-09-29","description":"Near-Astra performance for complex coding, computer use, and professional work at a lower cost.","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6.1-sol.toml","kind":"model","articles":[{"title":"Introducing GPT-6.1 Sol","url":"https://openai.com/index/introducing-gpt-6-1-sol","date":"2026-09-29","published_at":"2026-09-29T17:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-sonnet-5-5","name":"Claude Sonnet 5.5","lab":"anthropic","date":"2026-09-28","description":"Fast Claude model for everyday coding, agents, and knowledge work","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-5-5.toml","kind":"model","articles":[{"title":"Released Claude Sonnet 5.5","url":"https://platform.claude.com/docs/en/release-notes/overview#september-28-2026","date":"2026-09-28","published_at":"2026-09-28T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.8-live-with-live-avatar","name":"Gemini 3.8 Live with Live Avatar","lab":"google","date":"2026-09-24","description":"Live speech model","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-with-live-avatar/","kind":"model","articles":[{"title":"Introducing Gemini 3.8 Live with Live Avatar","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-with-live-avatar/","date":"2026-09-24","published_at":"2026-09-24T15:30:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-38-live-with-live-avatar/"]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.8-max-prime","name":"Qwen 3.8 Max Prime","lab":"alibaba","date":"2026-09-23","description":"High-throughput edition of Qwen3.8 Max for coding, professional work, multimodal understanding, and long-running agent workflows","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max-prime.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.8-flash-tts","name":"Gemini 3.8 Flash TTS","lab":"google","date":"2026-09-22","description":"Flagship text-to-speech model for expressive, studio-grade voices and long-form multi-speaker audio","context":8192,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/wav","audio/l16","audio/mulaw","audio/alaw"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-flash-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.8-flash-lite-tts","name":"Gemini 3.8 Flash Lite TTS","lab":"google","date":"2026-09-22","description":"Fast, cost-efficient text-to-speech model for high-volume narration and voice agent pipelines","context":8192,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/wav","audio/l16","audio/mulaw","audio/alaw"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-flash-lite-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-6-sol","name":"GPT-6 Sol","lab":"openai","date":"2026-09-22","description":"OpenAI model for complex coding and agentic workflows","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-sol.toml","kind":"model","articles":[{"title":"Introducing GPT-6 Sol and Luna","url":"https://openai.com/index/introducing-gpt-6-sol-and-luna","date":"2026-09-22","published_at":"2026-09-22T18:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-6-luna","name":"GPT-6 Luna","lab":"openai","date":"2026-09-22","description":"OpenAI's most efficient model for focused, high-volume tasks","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-luna.toml","kind":"model","articles":[{"title":"Introducing GPT-6 Sol and Luna","url":"https://openai.com/index/introducing-gpt-6-sol-and-luna","date":"2026-09-22","published_at":"2026-09-22T18:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-opus-5-5","name":"Claude Opus 5.5","lab":"anthropic","date":"2026-09-22","description":"Claude model for long-running agentic coding and knowledge work","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-5-5.toml","kind":"model","articles":[{"title":"Released Claude Opus 5.5","url":"https://platform.claude.com/docs/en/release-notes/overview#september-22-2026","date":"2026-09-22","published_at":"2026-09-22T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"xai/grok-4.7","name":"Grok 4.7","lab":"xai","date":"2026-09-21","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","context":500000,"output":500000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.7.toml","kind":"model","articles":[{"title":"Introducing Grok 4.7","url":"https://x.ai/news/grok-4-7","date":"2026-09-21","published_at":"2026-09-21T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3.8-livetranslate","name":"Qwen3.8-LiveTranslate","lab":"alibaba","date":"2026-09-18","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3.8-livetranslate","kind":"model","articles":[{"title":"Qwen3.8-LiveTranslate: Names the speaker. Carries the meaning.","url":"https://qwen.ai/blog?id=qwen3.8-livetranslate","date":"2026-09-18","published_at":"2026-09-18T09:30:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.8-omni-flash","name":"Qwen3.8 Omni Flash","lab":"alibaba","date":"2026-09-17","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","audio/amr","audio/wav","audio/3gpp","audio/aac","audio/mpeg","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-omni-flash.toml","kind":"model","articles":[{"title":"Qwen3.8-Omni-Flash: Omni Senses. Agentic Delivery.","url":"https://qwen.ai/blog?id=qwen3.8-omni-flash","date":"2026-09-18","published_at":"2026-09-18T07:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"xai/grok-voice-transcribe-2.0","name":"Grok Voice Transcribe 2.0","lab":"xai","date":"2026-09-17","description":"Speech-to-text model with word-level timestamps, speaker diarization, multichannel audio, and streaming","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mpeg","audio/ogg","audio/flac","audio/aac","audio/mp4"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-voice-transcribe-2.0.toml","kind":"model","articles":[{"title":"Introducing Grok Voice Transcribe 2.0","url":"https://x.ai/news/grok-voice-transcribe-2","date":"2026-09-18","published_at":"2026-09-18T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.8-live-extended-thinking","name":"Gemini 3.8 Live Extended Thinking","lab":"google","date":"2026-09-15","description":"Live API voice model with configurable background reasoning for multi-step real-time agents","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video","audio/pcm"],"output_modalities":["text","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-live-extended-thinking.toml","kind":"model","articles":[{"title":"Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/","date":"2026-09-15","published_at":"2026-09-15T17:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-3-8-live-and-3-8-live-extended-thinking/"]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.8-live","name":"Gemini 3.8 Live","lab":"google","date":"2026-09-15","description":"Low-latency Live API model for real-time voice agents with interleaved reasoning and async tools","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video","audio/pcm"],"output_modalities":["text","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-live.toml","kind":"model","articles":[{"title":"Introducing Gemini 3.8 Live and 3.8 Live Extended Thinking","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/","date":"2026-09-15","published_at":"2026-09-15T17:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-3-8-live-and-3-8-live-extended-thinking/"]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-image-2.1","name":"Qwen-Image-2.1","lab":"alibaba","date":"2026-09-14","description":"Unified text-to-image generation and image editing model with native RGBA transparency and reference-image editing","context":8192,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/tiff","image/webp","image/gif"],"output_modalities":["image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-image-2.1.toml","kind":"model","articles":[{"title":"Qwen-Image-2.1: Compact, Efficient, and Unified Image Creation","url":"https://qwen.ai/blog?id=qwen-image-2.1","date":"2026-09-20","published_at":"2026-09-20T12:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"moonshotai/kimi-k2.8-preview","name":"Kimi K2.8 Preview","lab":"moonshotai","date":"2026-09-11","description":"Kimi coding model with more efficient thinking and up to 1M context, available through Kimi Code","context":1048576,"output":null,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.8-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-live-1","name":"GPT-Live 1","lab":"openai","date":"2026-09-10","description":"Full-duplex voice model for natural conversations that delegates reasoning and tools to a backend agent","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-live-1.toml","kind":"model","articles":[{"title":"Build more natural voice experiences with GPT‑Live‑1 in the API","url":"https://openai.com/index/introducing-gpt-live-1-in-the-api","date":"2026-09-10","published_at":"2026-09-10T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","lab":"deepseek","date":"2026-09-10","description":"DeepSeek V4.1 Flash model for reasoning and agentic coding","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4.1-flash.toml","kind":"model","articles":[{"title":"DeepSeek-V4.1-Flash: Smarter, Faster, More Efficient","url":"https://api-docs.deepseek.com/news/news260910","date":"2026-09-10","published_at":"2026-09-10T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-image-2.5-sunburst","name":"GPT Image 2.5 Sunburst","lab":"openai","date":"2026-09-08","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-2.5-sunburst.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-image-2.5-flare","name":"GPT Image 2.5 Flare","lab":"openai","date":"2026-09-08","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-2.5-flare.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/alphagenome-atlas","name":"AlphaGenome Atlas","lab":"google","date":"2026-09-08","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/","kind":"tool","articles":[{"title":"AlphaGenome Atlas: A predictive map of every possible DNA letter change in the human genome","url":"https://deepmind.google/blog/alphagenome-atlas-a-predictive-map-of-every-possible-dna-letter-change-in-the-human-genome/","date":"2026-09-08","published_at":"2026-09-08T14:00:15+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-6-astra-fast","name":"GPT-6 Astra (Fast)","lab":"openai","date":"2026-09-04","description":"Fast variant of GPT-6 Astra for low-latency assistance and high-volume workloads.","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-astra-fast.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/weathernext-3","name":"WeatherNext 3","lab":"google","date":"2026-09-03","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/introducing-weathernext-3-our-most-advanced-and-accurate-global-weather-ai-model/","kind":"model","articles":[{"title":"Introducing WeatherNext 3, our most advanced and accurate global weather AI model","url":"https://deepmind.google/blog/introducing-weathernext-3-our-most-advanced-and-accurate-global-weather-ai-model/","date":"2026-09-03","published_at":"2026-09-03T15:02:08+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-drive-1.0","name":"Qwen-Drive-1.0","lab":"alibaba","date":"2026-09-03","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-drive-1.0","kind":"model","articles":[{"title":"Qwen-Drive-1.0: An Initial Step towards a Vision-Language Foundation Model for Autonomous Driving","url":"https://qwen.ai/blog?id=qwen-drive-1.0","date":"2026-09-03","published_at":"2026-09-03T00:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","lab":"openai","date":"2026-09-03","description":"GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-astra.toml","kind":"model","articles":[{"title":"GPT-6 Astra: A new generation of intelligence","url":"https://openai.com/index/gpt-6-astra","date":"2026-09-03","published_at":"2026-09-03T11:00:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"GPT-6 Astra: The next generation in intelligence for work","url":"https://openai.com/index/gpt-6-astra-next-generation-work","date":"2026-09-09","published_at":"2026-09-09T11:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.8-max-0902","name":"Qwen3.8 Max 0902","lab":"alibaba","date":"2026-09-02","description":"2026-09-02 upgraded snapshot of Qwen3.8 Max with stronger coding, collaborative agents, and multimodal document understanding","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max-0902.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/muse-spark-1.3","name":"Muse Spark 1.3","lab":"meta","date":"2026-09-02","description":"Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It improves long-horizon agent collaboration, instruction following, and coding efficiency relative to Muse Spark 1.2.","context":1048576,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","video/mp4","application/pdf","audio/mpeg","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.8-flash-cyber","name":"Gemini 3.8 Flash Cyber","lab":"google","date":"2026-09-02","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/","kind":"model","articles":[{"title":"Introducing Gemini 3.8 Flash and 3.8 Flash Cyber","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/","date":"2026-09-02","published_at":"2026-09-02T15:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-3-8-flash-and-38-flash-cyber/"]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.8-flash","name":"Gemini 3.8 Flash","lab":"google","date":"2026-09-02","description":"Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, and complex enterprise workflows","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-flash.toml","kind":"model","articles":[{"title":"Introducing Gemini 3.8 Flash and 3.8 Flash Cyber","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/3-8-flash-and-3-8-flash-cyber/","date":"2026-09-02","published_at":"2026-09-02T15:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-3-8-flash-and-38-flash-cyber/"]},{"title":"See what 4 builders are making with Gemini 3.8 Flash","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-flash-developers/","date":"2026-09-28","published_at":"2026-09-28T16:00:00+00:00","primary":false,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"meta/muse-voice-transcribe-1.0","name":"Muse Voice Transcribe 1.0","lab":"meta","date":"2026-09-01","description":"Speech-to-text model with speaker diarization and endpointing","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mpeg","audio/flac","audio/mp4","audio/ogg","audio/webm","audio/aac"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-voice-transcribe-1.0.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-mythos-5-1","name":"Claude Mythos 5.1","lab":"anthropic","date":"2026-09-01","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-mythos-5-1.toml","kind":"model","articles":[{"title":"Released Claude Fable 5.1 and Claude Mythos 5.1","url":"https://platform.claude.com/docs/en/release-notes/overview#september-1-2026","date":"2026-09-01","published_at":"2026-09-01T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-fable-5-1","name":"Claude Fable 5.1","lab":"anthropic","date":"2026-09-01","description":"Claude model for demanding reasoning and long-horizon agentic work","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-fable-5-1.toml","kind":"model","articles":[{"title":"Released Claude Fable 5.1 and Claude Mythos 5.1","url":"https://platform.claude.com/docs/en/release-notes/overview#september-1-2026","date":"2026-09-01","published_at":"2026-09-01T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-omni-1.1-flash","name":"Gemini Omni 1.1 Flash","lab":"google","date":"2026-08-27","description":"Video generation and editing model for scene extension, frame interpolation, and reference-guided multimodal control","context":1048576,"output":57920,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-omni-1.1-flash.toml","kind":"model","articles":[{"title":"Gemini Omni 1.1 Flash lets you build with more control","url":"https://blog.google/innovation-and-ai/technology/developers-tools/build-with-gemini-omni-1-1-flash/","date":"2026-08-27","published_at":"2026-08-27T16:00:00+00:00","primary":false,"publisher":"google","also":["https://deepmind.google/blog/gemini-omni-1-1-flash-lets-you-build-with-more-control/"]}],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.8-flash-next","name":"Qwen3.8 Flash Next","lab":"alibaba","date":"2026-08-26","description":"Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding","context":262144,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-flash-next.toml","kind":"model","articles":[{"title":"Qwen3.8-Flash-Next: A New Architecture, Towards Ultimate Cost-Efficiency","url":"https://qwen.ai/blog?id=qwen3.8-flash-next","date":"2026-08-26","published_at":"2026-08-26T12:30:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.8-flash","name":"Qwen3.8 Flash","lab":"alibaba","date":"2026-08-26","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.5-transcribe-live","name":"Gemini 3.5 Transcribe Live","lab":"google","date":"2026-08-26","description":"Speech transcription model for accurate audio-to-text and captioning workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/pcm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-transcribe-live.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.5-transcribe","name":"Gemini 3.5 Transcribe","lab":"google","date":"2026-08-26","description":"Speech-to-text model with language detection, speaker diarization, word timestamps, and custom vocabulary","context":98304,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-transcribe.toml","kind":"model","articles":[{"title":"Intelligent transcription with Gemini 3.5 Transcribe","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/","date":"2026-08-26","published_at":"2026-08-26T17:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/intelligent-transcription-with-gemini-3-5-transcribe/"]}],"confirmed":true,"date_source":"catalog"},{"id":"zhipuai/glm-5.3-flash","name":"GLM-5.3-Flash","lab":"zhipuai","date":"2026-08-26","description":"Native multimodal GLM model for efficient coding and long-horizon agent tasks","context":1000000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","video/x-matroska","video/quicktime","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.3-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-flash-vision-exp","name":"DeepSeek V4 Flash Vision Exp","lab":"deepseek","date":"2026-08-21","description":"Experimental multimodal DeepSeek V4 Flash model for image understanding, coding, and agentic work","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-vision-exp.toml","kind":"model","articles":[{"title":"DeepSeek-V4-Flash-Vision-Exp Release: Multimodal API Now Live","url":"https://api-docs.deepseek.com/news/news260821","date":null,"published_at":null,"primary":false,"publisher":"deepseek","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/wan3.0-video-prime","name":"Wan3.0-Video-Prime","lab":"alibaba","date":"2026-08-20","description":"High-speed Wan3.0 video model with the same four-modal references, up to 30 seconds","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp","video/mp4","audio/wav","audio/mpeg"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/wan3.0-video-prime.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.8-27b","name":"Qwen3.8 27B","lab":"alibaba","date":"2026-08-14","description":"Dense 27B vision-language model for coding, agent tasks, and image and video understanding","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-27b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-5.3","name":"GLM-5.3","lab":"zhipuai","date":"2026-08-14","description":"Flagship GLM model for long-horizon coding, agents, and complex project delivery","context":1000000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.7-flash","name":"Gemini 3.7 Flash","lab":"google","date":"2026-08-13","description":"High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.7-flash.toml","kind":"model","articles":[{"title":"Introducing Gemini 3.7 Flash","url":"https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/","date":"2026-08-13","published_at":"2026-08-13T17:00:00+00:00","primary":true,"publisher":"google","also":["https://deepmind.google/blog/introducing-gemini-3-7-flash/"]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","lab":"deepseek","date":"2026-08-13","description":"DeepSeek V4 Pro snapshot with million-token context and support for thinking and non-thinking modes","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro-0813.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.8-2.4t-a95b","name":"Qwen3.8 2.4T A95B","lab":"alibaba","date":"2026-08-12","description":"Open-weight sparse MoE (2.4T total, 95B active), the open-weight twin of Qwen3.8 Max for coding, research, complex reasoning, and agentic workflows","context":262144,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-2.4t-a95b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4.6","name":"Grok 4.6","lab":"xai","date":"2026-08-12","description":"xAI's frontier model for long-running agents, coding, knowledge work, and visual projects","context":500000,"output":500000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.6.toml","kind":"model","articles":[{"title":"Introducing Grok 4.6","url":"https://x.ai/news/grok-4-6","date":"2026-08-12","published_at":"2026-08-12T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/nemotron-3.5-lightning","name":"Nemotron 3.5 Lightning 30B A3B","lab":"nvidia","date":"2026-08-11","description":"Fast NVIDIA Nemotron MoE for reliable agentic tasks across enterprise workloads","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-lightning.toml","kind":"model","articles":[{"title":"NVIDIA Nemotron 3.5 Lightning and NeMo Switchyard Deliver Faster, Smarter, More Efficient Agentic AI","url":"https://blogs.nvidia.com/blog/nemotron-lightning-switchyard-rtx-dgx/","date":"2026-08-11","published_at":"2026-08-11T13:00:05+00:00","primary":true,"publisher":"nvidia","also":[]},{"title":"NVIDIA Nemotron 3.5 Lightning Delivers Fast, Accurate Specialized Task Execution for Long-Running Agents","url":"https://developer.nvidia.com/blog/nvidia-nemotron-3-5-lightning-delivers-fast-accurate-specialized-task-execution-for-long-running-agents/","date":"2026-08-11","published_at":"2026-08-11T13:01:07+00:00","primary":false,"publisher":"nvidia","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Nemotron 3.5 Lightning"]},{"id":"nvidia/nemo-switchyard","name":"NeMo Switchyard","lab":"nvidia","date":"2026-08-11","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://blogs.nvidia.com/blog/nemotron-lightning-switchyard-rtx-dgx/","kind":"tool","articles":[{"title":"NVIDIA Nemotron 3.5 Lightning and NeMo Switchyard Deliver Faster, Smarter, More Efficient Agentic AI","url":"https://blogs.nvidia.com/blog/nemotron-lightning-switchyard-rtx-dgx/","date":"2026-08-11","published_at":"2026-08-11T13:00:05+00:00","primary":true,"publisher":"nvidia","also":[]}],"confirmed":true,"date_source":"official"},{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","lab":"meta","date":"2026-08-10","description":"Muse Glimmer is a 30-billion-parameter open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark for always-on local agents, tool use, coding, and image understanding.","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-glimmer-30b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-imagine-image-2.0","name":"Grok Imagine Image 2.0","lab":"xai","date":"2026-08-07","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":64000,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/jpeg","image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-image-2.0.toml","kind":"model","articles":[{"title":"Imagine Image 2.0","url":"https://x.ai/news/grok-imagine-image-2","date":"2026-08-07","published_at":"2026-08-07T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5.6-cyber","name":"GPT-5.6 Cyber","lab":"openai","date":"2026-08-07","description":"Cybersecurity model for authorized vulnerability research and security testing","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-cyber.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/wan3.0-video","name":"Wan3.0","lab":"alibaba","date":"2026-08-06","description":"All-in-one video model for reference, editing and image-to-video generation with audio, up to 30 seconds","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp","video/mp4","audio/wav","audio/mpeg"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/wan3.0-video.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-image-3.0-pro","name":"Qwen-Image-3.0-Pro","lab":"alibaba","date":"2026-08-05","description":"Higher-quality Qwen-Image-3.0 for complex layouts, small text and photographic detail","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/tiff","image/webp","image/gif"],"output_modalities":["image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-image-3.0-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/muse-spark-1.2","name":"Muse Spark 1.2","lab":"meta","date":"2026-08-05","description":"Muse Spark 1.2 is a coding-focused update to Muse Spark 1.1 with improvements in code generation, complex debugging, codebase understanding, and end-to-end developer workflows.","context":1048576,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","video/mp4","application/pdf","audio/mpeg","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.8-max","name":"Qwen3.8 Max","lab":"alibaba","date":"2026-08-03","description":"2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max.toml","kind":"model","articles":[{"title":"Qwen3.8-Max: A New Bar for Coding and Cowork","url":"https://qwen.ai/blog?id=qwen3.8","date":"2026-08-03","published_at":"2026-08-03T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","lab":"deepseek","date":"2026-07-31","description":"Official DeepSeek V4 Flash release with enhanced agentic capabilities and integrated DSpark speculative decoding","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-0731.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-robotics-er-2-streaming-preview","name":"Gemini Robotics-ER 2 Streaming Preview","lab":"google","date":"2026-07-30","description":"Live API robotics model for low-latency robot agents over continuous audio and video","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","video","audio/pcm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-robotics-er-2-streaming-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-robotics-er-2-preview","name":"Gemini Robotics-ER 2 Preview","lab":"google","date":"2026-07-30","description":"Embodied reasoning model for robotics: spatial understanding, video progress, and multi-robot orchestration","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-robotics-er-2-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/lyria-3.5","name":"Lyria 3.5","lab":"google","date":"2026-07-29","description":"Music generation model for full-length songs with vocals and structure from text or image prompts","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","audio/mp3","audio/wav"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-3.5.toml","kind":"model","articles":[{"title":"We’re launching Lyria 3.5 in Google Flow Music, with advances across musicality, lyrics, vocals, and creative control","url":"https://deepmind.google/blog/were-launching-lyria-35-in-google-flow-music-with-advances-across-musicality-lyrics-vocals-and-creative-control/","date":"2026-07-29","published_at":"2026-07-29T16:02:10+00:00","primary":true,"publisher":"google","also":[]},{"title":"Create your best tracks yet with Lyria 3.5 in Gemini.","url":"https://blog.google/innovation-and-ai/products/gemini-app/better-tracks-lyria-gemini/","date":"2026-09-04","published_at":"2026-09-04T16:00:00+00:00","primary":false,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-voice-think-fast-2.0","name":"Grok Voice Think Fast 2.0","lab":"xai","date":"2026-07-29","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-voice-think-fast-2","kind":"model","articles":[{"title":"Introducing Grok Voice Think Fast 2.0","url":"https://x.ai/news/grok-voice-think-fast-2","date":"2026-07-29","published_at":"2026-07-29T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-robotics-2","name":"Gemini Robotics 2","lab":"google","date":"2026-07-28","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/","kind":"model","articles":[{"title":"Gemini Robotics 2 brings whole body intelligence to robots","url":"https://deepmind.google/blog/gemini-robotics-2-brings-whole-body-intelligence-to-robots/","date":"2026-07-28","published_at":"2026-07-28T13:21:37+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-transcribe","name":"GPT-Transcribe","lab":"openai","date":"2026-07-28","description":"High-accuracy speech-to-text model for audio files and committed Realtime turns","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm","audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-transcribe.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-live-transcribe","name":"GPT-Live-Transcribe","lab":"openai","date":"2026-07-28","description":"Low-latency streaming speech-to-text model with keyword and language hints","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-live-transcribe.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-opus-5","name":"Claude Opus 5","lab":"anthropic","date":"2026-07-24","description":"Strongest Claude Opus model for coding, agents, and professional work","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-5.toml","kind":"model","articles":[{"title":"Released Claude Opus 5","url":"https://platform.claude.com/docs/en/release-notes/overview#july-24-2026","date":"2026-07-24","published_at":"2026-07-24T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]},{"title":"Introducing Claude Opus 5","url":"https://www.anthropic.com/news/claude-opus-5","date":"2026-07-24","published_at":"2026-07-24T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-image-3.0","name":"Qwen-Image-3.0","lab":"alibaba","date":"2026-07-21","description":"Unified image generation and editing model with dense layouts and small-text rendering","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/tiff","image/webp","image/gif"],"output_modalities":["image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-image-3.0.toml","kind":"model","articles":[{"title":"Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge","url":"https://qwen.ai/blog?id=qwen-image-3.0","date":"2026-07-21","published_at":"2026-07-21T06:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.6-flash","name":"Gemini 3.6 Flash","lab":"google","date":"2026-07-21","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.6-flash.toml","kind":"model","articles":[{"title":"Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber","url":"https://deepmind.google/blog/introducing-gemini-3-6-flash-3-5-flash-lite-and-3-5-flash-cyber/","date":"2026-07-21","published_at":"2026-07-21T15:16:30+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.5-flash-lite","name":"Gemini 3.5 Flash Lite","lab":"google","date":"2026-07-21","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-flash-lite.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.8-max-preview","name":"Qwen3.8 Max Preview","lab":"alibaba","date":"2026-07-19","description":"Preview Qwen flagship for million-token multimodal reasoning and long-horizon agentic workflows","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.5-flash-cyber","name":"Gemini 3.5 Flash Cyber","lab":"google","date":"2026-07-17","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/","kind":"model","articles":[{"title":"Introducing Gemini 3.5 Flash Cyber","url":"https://deepmind.google/blog/introducing-gemini-3-5-flash-cyber/","date":"2026-07-17","published_at":"2026-07-17T15:00:11+00:00","primary":true,"publisher":"google","also":[]},{"title":"Introducing Gemini 3.6 Flash, 3.5 Flash-Lite, and 3.5 Flash Cyber","url":"https://deepmind.google/blog/introducing-gemini-3-6-flash-3-5-flash-lite-and-3-5-flash-cyber/","date":"2026-07-21","published_at":"2026-07-21T15:16:30+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"nvidia/nemotron-3-embed-1b","name":"Nemotron 3 Embed 1B","lab":"nvidia","date":"2026-07-16","description":"Open text embedding model for retrieval, RAG, and code search","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-embed-1b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-ocr-4-1","name":"Mistral OCR 4.1","lab":"mistral","date":"2026-07-16","description":"Document OCR model with paragraph-level bounding boxes, block labels, and confidence scores","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["image/jpeg","image/png","image/avif","image/tiff","image/gif","image/heic","image/heif","image/bmp","image/webp","application/pdf","text/csv","text/plain","text/xml","text/troff"],"output_modalities":["text","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-ocr-4-1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k3","name":"Kimi K3","lab":"moonshotai","date":"2026-07-16","description":"Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work","context":1048576,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k3.toml","kind":"model","articles":[{"title":"Kimi K3 Tech Blog: Open Frontier Intelligence","url":"https://www.kimi.ai/blog/kimi-k3","date":null,"published_at":null,"primary":false,"publisher":"moonshotai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.7-flash","name":"Qwen3.7 Flash","lab":"alibaba","date":"2026-07-15","description":"Lightweight multimodal Qwen model for high-throughput text, image, and video tasks","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.6-terra","name":"GPT-5.6 Terra","lab":"openai","date":"2026-07-09","description":"Balanced GPT-5.6 model for capable, cost-efficient everyday work","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-terra.toml","kind":"model","articles":[{"title":"GPT-5.6: Frontier intelligence that scales with your ambition","url":"https://openai.com/index/gpt-5-6","date":"2026-07-09","published_at":"2026-07-09T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["GPT-5.6"]},{"id":"openai/gpt-5.6-sol","name":"GPT-5.6 Sol","lab":"openai","date":"2026-07-09","description":"Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-sol.toml","kind":"model","articles":[{"title":"GPT-5.6: Frontier intelligence that scales with your ambition","url":"https://openai.com/index/gpt-5-6","date":"2026-07-09","published_at":"2026-07-09T10:00:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"Previewing GPT-5.6 Sol: a next-generation model","url":"https://openai.com/index/previewing-gpt-5-6-sol","date":"2026-06-26","published_at":"2026-06-26T10:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["GPT-5.6"]},{"id":"openai/gpt-5.6-luna","name":"GPT-5.6 Luna","lab":"openai","date":"2026-07-09","description":"Cost-efficient GPT-5.6 model for fast, high-volume workloads","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-luna.toml","kind":"model","articles":[{"title":"GPT-5.6: Frontier intelligence that scales with your ambition","url":"https://openai.com/index/gpt-5-6","date":"2026-07-09","published_at":"2026-07-09T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["GPT-5.6"]},{"id":"mistral/robostral-navigate","name":"Robostral Navigate","lab":"mistral","date":"2026-07-08","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/robostral-navigate/","kind":"model","articles":[{"title":"Robostral Navigate: single-camera AI navigation","url":"https://mistral.ai/news/robostral-navigate/","date":"2026-07-08","published_at":"2026-07-08T12:00:59+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-4.5","name":"Grok 4.5","lab":"xai","date":"2026-07-08","description":"xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk","context":500000,"output":500000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.5.toml","kind":"model","articles":[{"title":"Introducing Grok 4.5","url":"https://x.ai/news/grok-4-5","date":"2026-07-16","published_at":"2026-07-16T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-live","name":"GPT-Live","lab":"openai","date":"2026-07-08","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://openai.com/index/introducing-gpt-live","kind":"model","articles":[{"title":"Introducing GPT-Live","url":"https://openai.com/index/introducing-gpt-live","date":"2026-07-08","published_at":"2026-07-08T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"meta/muse-video","name":"Muse Video","lab":"meta","date":"2026-07-07","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://ai.meta.com/blog/introducing-muse-image-muse-video-msl/","kind":"model","articles":[{"title":"Introducing Muse Image and Muse Video","url":"https://ai.meta.com/blog/introducing-muse-image-muse-video-msl/","date":"2026-07-07","published_at":"2026-07-07T00:00:00+00:00","primary":true,"publisher":"meta","also":[]}],"confirmed":true,"date_source":"official"},{"id":"meta/muse-image-1.0","name":"Muse Image","lab":"meta","date":"2026-07-07","description":"Agentic image generation and editing model that plans, searches and refines before rendering","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp"],"output_modalities":["image/webp","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-image-1.0.toml","kind":"model","articles":[{"title":"Introducing Muse Image and Muse Video","url":"https://ai.meta.com/blog/introducing-muse-image-muse-video-msl/","date":"2026-07-07","published_at":"2026-07-07T00:00:00+00:00","primary":true,"publisher":"meta","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-realtime-2.1-mini","name":"GPT-Realtime-2.1 Mini","lab":"openai","date":"2026-07-06","description":"Distilled realtime reasoning model for faster, lower-cost voice interactions","context":128000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-2.1-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime-2.1","name":"GPT-Realtime-2.1","lab":"openai","date":"2026-07-06","description":"Realtime speech-to-speech model with configurable reasoning, tool use, and robust voice-agent behavior","context":128000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-2.1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/leanstral-1.5","name":"Leanstral 1.5","lab":"mistral","date":"2026-07-02","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/leanstral-1-5/","kind":"model","articles":[{"title":"Leanstral 1.5: Proof Abundance for All","url":"https://mistral.ai/news/leanstral-1-5/","date":"2026-07-02","published_at":"2026-07-02T13:55:54+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.1-flash-lite-image","name":"Nano Banana 2 Lite","lab":"google","date":"2026-06-30","description":"Fastest, most cost-efficient Gemini image model for high-volume 1K generation and editing","context":65536,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite-image.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-omni-flash-preview","name":"Gemini Omni Flash Preview","lab":"google","date":"2026-06-30","description":"Video generation and editing model for fast, conversational text- and image-to-video workflows","context":1048576,"output":57920,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-omni-flash-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-sonnet-5","name":"Claude Sonnet 5","lab":"anthropic","date":"2026-06-30","description":"Everyday Claude agent model for coding, planning, browsing, and general work","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-5.toml","kind":"model","articles":[{"title":"Released Claude Sonnet 5","url":"https://platform.claude.com/docs/en/release-notes/overview#june-30-2026","date":"2026-06-30","published_at":"2026-06-30T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-agentworld","name":"Qwen-AgentWorld","lab":"alibaba","date":"2026-06-23","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-agentworld","kind":"tool","articles":[{"title":"Qwen-AgentWorld: Language World Models for General Agents","url":"https://qwen.ai/blog?id=qwen-agentworld","date":"2026-06-23","published_at":"2026-06-23T03:30:30+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"mistral/mistral-ocr-4","name":"Mistral OCR 4","lab":"mistral","date":"2026-06-23","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/ocr-4/","kind":"model","articles":[{"title":"Mistral OCR 4 : SOTA OCR for Document Intelligence","url":"https://mistral.ai/news/ocr-4/","date":"2026-06-23","published_at":"2026-06-23T12:00:48+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-robotworld","name":"Qwen-RobotWorld","lab":"alibaba","date":"2026-06-16","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-robotworld","kind":"tool","articles":[{"title":"Qwen-RobotWorld: Boundless Worlds for Embodied Agents","url":"https://qwen.ai/blog?id=qwen-robotworld","date":"2026-06-16","published_at":"2026-06-16T00:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-robotnav","name":"Qwen-RobotNav","lab":"alibaba","date":"2026-06-16","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-robotnav","kind":"model","articles":[{"title":"Qwen-RobotNav: A Scalable Navigation Model Designed for an Agentic Navigation System","url":"https://qwen.ai/blog?id=qwen-robotnav","date":"2026-06-16","published_at":"2026-06-16T00:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-robotmanip","name":"Qwen-RobotManip","lab":"alibaba","date":"2026-06-16","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-robotmanip","kind":"model","articles":[{"title":"Qwen-RobotManip: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","url":"https://qwen.ai/blog?id=qwen-robotmanip","date":"2026-06-16","published_at":"2026-06-16T00:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/happyhorse-1.1","name":"HappyHorse-1.1","lab":"alibaba","date":"2026-06-16","description":"Video model for text, image and reference to video with smoother motion and stronger consistency","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/happyhorse-1.1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-5.2","name":"GLM-5.2","lab":"zhipuai","date":"2026-06-13","description":"Open flagship GLM for long-horizon coding agents and million-token context work","context":1000000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2.7-code-highspeed","name":"Kimi K2.7 Code Highspeed","lab":"moonshotai","date":"2026-06-12","description":"Lower-latency Kimi Code variant for interactive edits and coding-agent loops","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.7-code-highspeed.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2.7-code","name":"Kimi K2.7 Code","lab":"moonshotai","date":"2026-06-12","description":"Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.7-code.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-4-12b-it","name":"Gemma 4 12B IT","lab":"google","date":"2026-06-09","description":"Compact Gemma 4 instruction model for open, self-hosted chat and reasoning","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-12b-it.toml","kind":"model","articles":[{"title":"Introducing Gemma 4 12B: a unified, encoder-free multimodal model","url":"https://deepmind.google/blog/introducing-gemma-4-12b-a-unified-encoder-free-multimodal-model/","date":"2026-06-09","published_at":"2026-06-09T14:10:19+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemma 4 12B"]},{"id":"google/gemini-3.5-live-translate-preview","name":"Gemini 3.5 Live Translate Preview","lab":"google","date":"2026-06-09","description":"Low-latency audio-to-audio model for real-time speech translation across 70+ languages","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/pcm"],"output_modalities":["audio/pcm","text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-live-translate-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","lab":"google","date":"2026-06-09","description":"Gemma 4 based discrete text diffusion model for fast chat, reasoning, and tool use","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/diffusiongemma-26b-a4b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-mythos-5","name":"Claude Mythos 5","lab":"anthropic","date":"2026-06-09","description":"Restricted Claude model for advanced cybersecurity and biology research workflows","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-mythos-5.toml","kind":"model","articles":[{"title":"Released Claude Fable 5 and Claude Mythos 5","url":"https://platform.claude.com/docs/en/release-notes/overview#june-9-2026","date":"2026-06-09","published_at":"2026-06-09T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-fable-5","name":"Claude Fable 5","lab":"anthropic","date":"2026-06-09","description":"Claude model for creative writing, analysis, and controlled agent workflows","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-fable-5.toml","kind":"model","articles":[{"title":"Released Claude Fable 5 and Claude Mythos 5","url":"https://platform.claude.com/docs/en/release-notes/overview#june-9-2026","date":"2026-06-09","published_at":"2026-06-09T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","lab":"nvidia","date":"2026-06-04","description":"Largest Nemotron 3 model for maximum open-weight reasoning and agent accuracy","context":1000000,"output":128000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-ultra-550b-a55b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","lab":"nvidia","date":"2026-06-02","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/gif","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-content-safety.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus","lab":"alibaba","date":"2026-06-01","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","context":1000000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-plus.toml","kind":"model","articles":[{"title":"Qwen3.7-Plus: Multimodal Agent Intelligence","url":"https://qwen.ai/blog?id=qwen3.7-plus","date":"2026-06-01","published_at":"2026-06-01T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","lab":"xai","date":"2026-05-30","description":"Video model for text-to-video, image-to-video, and reference-to-video generation with optional voice references","context":1024,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp","audio"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-video-1.5.toml","kind":"model","articles":[{"title":"Grok Imagine Video 1.5","url":"https://x.ai/news/grok-imagine-video-1-5","date":"2026-06-16","published_at":"2026-06-16T00:00:00+00:00","primary":true,"publisher":"xai","also":[]},{"title":"Imagine Video 1.5 with References","url":"https://x.ai/news/grok-imagine-video-1-5-references","date":"2026-07-31","published_at":"2026-07-31T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-vla","name":"Qwen-VLA","lab":"alibaba","date":"2026-05-29","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwenvla","kind":"model","articles":[{"title":"Qwen-VLA: From Understanding the World to Acting in It","url":"https://qwen.ai/blog?id=qwenvla","date":"2026-05-29","published_at":"2026-05-29T09:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3-pro-image","name":"Nano Banana Pro","lab":"google","date":"2026-05-28","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","context":65536,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-image.toml","kind":"model","articles":[{"title":"Build with Nano Banana Pro, our Gemini 3 Pro Image model","url":"https://deepmind.google/blog/build-with-nano-banana-pro-our-gemini-3-pro-image-model/","date":"2025-11-20","published_at":"2025-11-20T15:11:14+00:00","primary":false,"publisher":"google","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.1-flash-image","name":"Nano Banana 2","lab":"google","date":"2026-05-28","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":131072,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-image.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-8","name":"Claude Opus 4.8","lab":"anthropic","date":"2026-05-28","description":"Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-8.toml","kind":"model","articles":[{"title":"Released Claude Opus 4.8","url":"https://platform.claude.com/docs/en/release-notes/overview#may-28-2026","date":"2026-05-28","published_at":"2026-05-28T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3.7-max","name":"Qwen3.7 Max","lab":"alibaba","date":"2026-05-21","description":"Qwen frontier model tuned for agent frameworks, coding assistants, and long tasks","context":1000000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-max.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.7","name":"Qwen3.7","lab":"alibaba","date":"2026-05-20","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3.7","kind":"model","articles":[{"title":"Qwen3.7: The Agent Frontier","url":"https://qwen.ai/blog?id=qwen3.7","date":"2026-05-20","published_at":"2026-05-20T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.5-livetranslate","name":"Qwen3.5-LiveTranslate","lab":"alibaba","date":"2026-05-19","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3.5-livetranslate","kind":"model","articles":[{"title":"Qwen3.5-LiveTranslate: From Sound to Sight, From Word to Right","url":"https://qwen.ai/blog?id=qwen3.5-livetranslate","date":"2026-05-19","published_at":"2026-05-19T09:40:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.5-flash","name":"Gemini 3.5 Flash","lab":"google","date":"2026-05-19","description":"Fast Gemini model balancing multimodal reasoning, tool use, and cost","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-flash.toml","kind":"model","articles":[{"title":"Introducing computer use in Gemini 3.5 Flash","url":"https://deepmind.google/blog/introducing-computer-use-in-gemini-3-5-flash/","date":"2026-06-24","published_at":"2026-06-24T16:30:01+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.5","name":"Gemini 3.5","lab":"google","date":"2026-05-15","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/gemini-3-5-frontier-intelligence-with-action/","kind":"model","articles":[{"title":"Gemini 3.5: frontier intelligence with action","url":"https://deepmind.google/blog/gemini-3-5-frontier-intelligence-with-action/","date":"2026-05-15","published_at":"2026-05-15T22:50:12+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-realtime-translate","name":"GPT-Realtime-Translate","lab":"openai","date":"2026-05-07","description":"Streaming speech-to-speech translation model for live multilingual audio","context":16000,"output":2000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/pcm"],"output_modalities":["text","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-translate.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime-2","name":"GPT-Realtime-2","lab":"openai","date":"2026-05-07","description":"Realtime speech-to-speech model with configurable reasoning and reliable tool use for voice agents","context":128000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime-whisper","name":"GPT Realtime Whisper","lab":"openai","date":"2026-05-07","description":"Streaming speech-to-text model for low-latency transcript deltas from live audio","context":16000,"output":2000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-whisper.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.5-instant","name":"GPT-5.5 Instant","lab":"openai","date":"2026-05-05","description":"Compact GPT model for low-latency assistance and high-volume workloads","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5-instant.toml","kind":"model","articles":[{"title":"GPT-5.5 Instant: smarter, clearer, and more personalized","url":"https://openai.com/index/gpt-5-5-instant","date":"2026-05-05","published_at":"2026-05-05T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-scope","name":"Qwen-Scope","lab":"alibaba","date":"2026-04-30","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-scope","kind":"tool","articles":[{"title":"Qwen-Scope: Decoding Intelligence, Unleashing Potential","url":"https://qwen.ai/blog?id=qwen-scope","date":"2026-04-30","published_at":"2026-04-30T04:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"mistral/mistral-medium-3-5","name":"Mistral Medium 3.5","lab":"mistral","date":"2026-04-30","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":262144,"output":209715,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-3-5.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-medium-2604","name":"Mistral Medium 3.5","lab":"mistral","date":"2026-04-29","description":"Balanced Mistral model for enterprise assistants, multilingual work, and tools","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-2604.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni 30B A3B Reasoning","lab":"nvidia","date":"2026-04-28","description":"Open Nemotron omni model combining reasoning with text, vision, and audio","context":256000,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","audio/wav","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.6-flash","name":"Qwen3.6 Flash","lab":"alibaba","date":"2026-04-27","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":1000000,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-pro","name":"DeepSeek V4 Pro","lab":"deepseek","date":"2026-04-24","description":"Open MoE flagship with million-token context for coding and long agent runs","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro.toml","kind":"model","articles":[{"title":"DeepSeek-V4-Pro GA Release","url":"https://api-docs.deepseek.com/news/news260813","date":"2026-08-13","published_at":"2026-08-13T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-preview","name":"DeepSeek V4 Preview","lab":"deepseek","date":"2026-04-24","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://api-docs.deepseek.com/news/news260424","kind":"model","articles":[{"title":"DeepSeek V4 Preview Release","url":"https://api-docs.deepseek.com/news/news260424","date":"2026-04-24","published_at":"2026-04-24T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"official"},{"id":"deepseek/deepseek-v4-flash","name":"DeepSeek V4 Flash","lab":"deepseek","date":"2026-04-24","description":"Fast DeepSeek V4 lane for economical reasoning, coding, and long-context work","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-voice-think-fast-1.0","name":"Grok Voice Think Fast 1.0","lab":"xai","date":"2026-04-23","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-voice-think-fast-1","kind":"model","articles":[{"title":"Grok Voice Think Fast 1.0","url":"https://x.ai/news/grok-voice-think-fast-1","date":"2026-04-23","published_at":"2026-04-23T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-5.5-pro","name":"GPT-5.5 Pro","lab":"openai","date":"2026-04-23","description":"Highest-accuracy GPT-5.5 tier for slower, precision-heavy reasoning and coding","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.5","name":"GPT-5.5","lab":"openai","date":"2026-04-23","description":"Default frontier GPT for coding, computer use, research, and knowledge work","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5.toml","kind":"model","articles":[{"title":"Introducing GPT-5.5","url":"https://openai.com/index/introducing-gpt-5-5","date":"2026-04-23","published_at":"2026-04-23T11:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-pro-0423","name":"DeepSeek V4 Pro 0423","lab":"deepseek","date":"2026-04-23","description":"DeepSeek V4 Pro initial snapshot with million-token context and support for thinking and non-thinking modes","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro-0423.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v4-flash-0423","name":"DeepSeek V4 Flash 0423","lab":"deepseek","date":"2026-04-23","description":"Initial DeepSeek V4 Flash snapshot for economical reasoning, coding, and million-token agent workloads","context":1000000,"output":384000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-0423.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.6-27b","name":"Qwen3.6 27B","lab":"alibaba","date":"2026-04-22","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-27b.toml","kind":"model","articles":[{"title":"Qwen3.6-27B: Flagship-Level Coding in a 27B Dense Model","url":"https://qwen.ai/blog?id=qwen3.6-27b","date":"2026-04-22","published_at":"2026-04-22T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/happyhorse-1.0","name":"HappyHorse-1.0","lab":"alibaba","date":"2026-04-22","description":"Video model for text, image and reference to video with realistic motion","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/happyhorse-1.0.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-embedding-2","name":"Gemini Embedding 2","lab":"google","date":"2026-04-22","description":"Multimodal embedding model mapping text, images, video, audio, and PDFs into a unified embedding space","context":8192,"output":3072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","audio/mp3","audio/wav","video/mp4","video/mov","application/pdf"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-embedding-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/deep-research-preview-04-2026","name":"Gemini Deep Research Preview","lab":"google","date":"2026-04-21","description":"Agentic model for autonomous multi-step research, synthesis, and cited reports","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/deep-research-preview-04-2026.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-image-2","name":"GPT-Image-2","lab":"openai","date":"2026-04-21","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.4-image-2","name":"GPT-5.4 Image 2","lab":"openai","date":"2026-04-21","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":272000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["image/jpeg","image/png","image/gif","image/webp","text","application/pdf"],"output_modalities":["image/png","image/jpeg","image/webp","text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-image-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/deep-research-max-preview-04-2026","name":"Deep Research Max Preview","lab":"google","date":"2026-04-21","description":"Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/deep-research-max-preview-04-2026.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","lab":"moonshotai","date":"2026-04-20","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.6.toml","kind":"model","articles":[{"title":"Kimi K2.6 Tech Blog: Advancing Open-Source Coding","url":"https://www.kimi.ai/blog/kimi-k2-6","date":null,"published_at":null,"primary":false,"publisher":"moonshotai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","lab":"alibaba","date":"2026-04-18","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","context":262144,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-max-preview.toml","kind":"model","articles":[{"title":"Qwen3.6-Max-Preview: Smarter, Sharper, Still Evolving","url":"https://qwen.ai/blog?id=qwen3.6-max-preview","date":"2026-04-18","published_at":"2026-04-18T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-4.3","name":"Grok 4.3","lab":"xai","date":"2026-04-17","description":"xAI's default Grok for chat, coding, agentic tools, and lower hallucination risk","context":1000000,"output":30000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-build-0.1","name":"Grok Build 0.1","lab":"xai","date":"2026-04-16","description":"Fast Grok coding model tuned for agentic engineering and iterative edits","context":256000,"output":256000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-build-0.1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-7","name":"Claude Opus 4.7","lab":"anthropic","date":"2026-04-16","description":"Stronger Opus tier for advanced software work and high-stakes reasoning","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-7.toml","kind":"model","articles":[{"title":"Released Claude Opus 4.7","url":"https://platform.claude.com/docs/en/release-notes/overview#april-16-2026","date":"2026-04-16","published_at":"2026-04-16T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","lab":"alibaba","date":"2026-04-15","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-35b-a3b.toml","kind":"model","articles":[{"title":"Qwen3.6-35B-A3B: Agentic Coding Power, Now Open to All","url":"https://qwen.ai/blog?id=qwen3.6-35b-a3b","date":"2026-04-15","published_at":"2026-04-15T02:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.1-flash-tts-preview","name":"Gemini 3.1 Flash TTS Preview","lab":"google","date":"2026-04-15","description":"Low-latency speech generation with steerable prompts and expressive audio tags","context":8192,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/l16"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-tts-preview.toml","kind":"model","articles":[{"title":"Gemini 3.1 Flash TTS: the next generation of expressive AI speech","url":"https://deepmind.google/blog/gemini-3-1-flash-tts-the-next-generation-of-expressive-ai-speech/","date":"2026-04-15","published_at":"2026-04-15T16:03:19+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3.1 Flash TTS"]},{"id":"google/gemini-robotics-er-1.6-preview","name":"Gemini Robotics-ER 1.6 Preview","lab":"google","date":"2026-04-14","description":"Vision-language model for embodied reasoning: spatial understanding, task planning, and physical-world agentic robotics","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-robotics-er-1.6-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/muse-spark-1.1","name":"Muse Spark 1.1","lab":"meta","date":"2026-04-08","description":"Muse Spark is a natively multimodal reasoning model with support for tool-use, visual chain of thought, and multi-agent orchestration.","context":1048576,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf","video/mp4"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.1.toml","kind":"model","articles":[{"title":"Introducing Muse Spark: Scaling Towards Personal Superintelligence","url":"https://ai.meta.com/blog/introducing-muse-spark-msl/","date":"2026-04-08","published_at":"2026-04-08T00:00:00+00:00","primary":true,"publisher":"meta","also":[]},{"title":"Introducing Muse Spark 1.1","url":"https://ai.meta.com/blog/introducing-muse-spark-meta-model-api/","date":"2026-07-09","published_at":"2026-07-09T00:00:00+00:00","primary":true,"publisher":"meta","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Muse Spark"]},{"id":"zhipuai/glm-5.1","name":"GLM-5.1","lab":"zhipuai","date":"2026-04-07","description":"Strong GLM coding model for agentic engineering, terminals, and repository generation","context":200000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.1.toml","kind":"model","articles":[{"title":"GLM-5.1","url":"https://docs.z.ai/release-notes/new-released#2026-04-07","date":"2026-04-07","published_at":"2026-04-07T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/wan2.7","name":"Wan2.7","lab":"alibaba","date":"2026-04-03","description":"Video model for text, image and reference to video, with mixed image and video references and voice timbre cloning","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp","video/mp4","audio/wav","audio/mpeg"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/wan2.7.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-imagine-image-quality","name":"Grok Imagine Image Quality","lab":"xai","date":"2026-04-03","description":"Higher-fidelity Grok Imagine image model for prompt-driven generation, editing, and visual design workflows","context":16000,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/jpeg","image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-image-quality.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-4-E4B-it","name":"Gemma 4 E4B IT","lab":"google","date":"2026-04-02","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","audio/mpeg","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-E4B-it.toml","kind":"model","articles":[{"title":"Gemma 4: Byte for byte, the most capable open models","url":"https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/","date":"2026-04-02","published_at":"2026-04-02T16:00:49+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemma 4"]},{"id":"google/gemma-4-E2B-it","name":"Gemma 4 E2B IT","lab":"google","date":"2026-04-02","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","audio/mpeg","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-E2B-it.toml","kind":"model","articles":[{"title":"Gemma 4: Byte for byte, the most capable open models","url":"https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/","date":"2026-04-02","published_at":"2026-04-02T16:00:49+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemma 4"]},{"id":"google/gemma-4-31b-it","name":"Gemma 4 31B IT","lab":"google","date":"2026-04-02","description":"Largest Gemma 4 instruction model for open, self-hosted chat and reasoning","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-31b-it.toml","kind":"model","articles":[{"title":"Gemma 4: Byte for byte, the most capable open models","url":"https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/","date":"2026-04-02","published_at":"2026-04-02T16:00:49+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemma 4"]},{"id":"google/gemma-4-26b-a4b-it","name":"Gemma 4 26B A4B IT","lab":"google","date":"2026-04-02","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-26b-a4b-it.toml","kind":"model","articles":[{"title":"Gemma 4: Byte for byte, the most capable open models","url":"https://deepmind.google/blog/gemma-4-byte-for-byte-the-most-capable-open-models/","date":"2026-04-02","published_at":"2026-04-02T16:00:49+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemma 4"]},{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus","lab":"alibaba","date":"2026-04-01","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","context":1000000,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-plus.toml","kind":"model","articles":[{"title":"Qwen3.6-Plus: Towards Real World Agents","url":"https://qwen.ai/blog?id=qwen3.6","date":"2026-04-01","published_at":"2026-04-01T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"zhipuai/glm-5v-turbo","name":"GLM-5V-Turbo","lab":"zhipuai","date":"2026-04-01","description":"Fast GLM vision model for screenshots, documents, and multimodal agent tasks","context":200000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","video/quicktime","video/x-matroska","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5v-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/veo-3.1-lite-generate-preview","name":"Veo 3.1 Lite Preview","lab":"google","date":"2026-03-31","description":"Video model for prompt-guided generation, editing, and motion workflows","context":1024,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-lite-generate-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-omni","name":"Qwen3.5-Omni","lab":"alibaba","date":"2026-03-29","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3.5-omni","kind":"model","articles":[{"title":"Qwen3.5-Omni: Scaling Up, Toward Native Omni-Modal AGI","url":"https://qwen.ai/blog?id=qwen3.5-omni","date":"2026-03-29","published_at":"2026-03-29T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3.1-flash-live-preview","name":"Gemini 3.1 Flash Live Preview","lab":"google","date":"2026-03-26","description":"High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video","audio/pcm"],"output_modalities":["text","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-live-preview.toml","kind":"model","articles":[{"title":"Gemini 3.1 Flash Live: Making audio AI more natural and reliable","url":"https://deepmind.google/blog/gemini-3-1-flash-live-making-audio-ai-more-natural-and-reliable/","date":"2026-03-26","published_at":"2026-03-26T15:23:35+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3.1 Flash Live"]},{"id":"google/lyria-3-pro-preview","name":"Lyria 3 Pro Preview","lab":"google","date":"2026-03-25","description":"Music generation model for full-length songs from text or images with vocals and structure","context":131072,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","audio/mp3"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-3-pro-preview.toml","kind":"model","articles":[{"title":"Lyria 3 Pro: Create longer tracks in more","url":"https://deepmind.google/blog/lyria-3-pro-create-longer-tracks-in-more/","date":"2026-03-25","published_at":"2026-03-25T16:01:39+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Lyria 3 Pro"]},{"id":"google/lyria-3-clip-preview","name":"Lyria 3 Clip Preview","lab":"google","date":"2026-03-25","description":"Music generation model for short 30-second clips, loops, and previews from text or image prompts","context":131072,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","audio/mp3"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-3-clip-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/voxtral-mini-tts-2603","name":"Voxtral Mini TTS","lab":"mistral","date":"2026-03-23","description":"Multilingual text-to-speech model with zero-shot voice cloning","context":null,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/pcm","audio/wav","audio/mpeg","audio/flac","audio/opus"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/voxtral-mini-tts-2603.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-cascade-2-30b-a3b","name":"Nemotron Cascade 2 30B A3B","lab":"nvidia","date":"2026-03-19","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":256000,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-cascade-2-30b-a3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-max-preview","name":"Qwen3.5-Max-Preview","lab":"alibaba","date":"2026-03-18","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3.5-max-preview","kind":"model","articles":[{"title":"Qwen3.5-Max-Preview Now Available on Arena","url":"https://qwen.ai/blog?id=qwen3.5-max-preview","date":"2026-03-18","published_at":"2026-03-18T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-5.4-nano","name":"GPT-5.4 nano","lab":"openai","date":"2026-03-17","description":"Cheapest GPT-5.4 lane for simple routing, extraction, and bulk automation","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-nano.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.4-mini","name":"GPT-5.4 mini","lab":"openai","date":"2026-03-17","description":"Strong small GPT for coding subagents, quick tool use, and high-volume work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-mini.toml","kind":"model","articles":[{"title":"Introducing GPT-5.4 mini and nano","url":"https://openai.com/index/introducing-gpt-5-4-mini-and-nano","date":"2026-03-17","published_at":"2026-03-17T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/nemotron-voicechat","name":"Nemotron VoiceChat","lab":"nvidia","date":"2026-03-16","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-voicechat.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-3-content-safety","name":"Nemotron 3 Content Safety","lab":"nvidia","date":"2026-03-16","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-content-safety.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-small-2603","name":"Mistral Small 4","lab":"mistral","date":"2026-03-16","description":"Fast Mistral production model for chat, extraction, and cost-sensitive agents","context":256000,"output":256000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-2603.toml","kind":"model","articles":[{"title":"Introducing Mistral Small 4","url":"https://mistral.ai/news/mistral-small-4/","date":"2026-03-16","published_at":"2026-03-16T21:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/leanstral","name":"Leanstral","lab":"mistral","date":"2026-03-16","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/leanstral/","kind":"model","articles":[{"title":"Leanstral: Open-Source foundation for trustworthy vibe-coding","url":"https://mistral.ai/news/leanstral/","date":"2026-03-16","published_at":"2026-03-16T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-tts","name":"Grok TTS","lab":"xai","date":"2026-03-16","description":"Convert text into spoken audio with a single API call. The API supports a rich set of expressive voices, inline speech tags for fine-grained delivery control, and output formats from high-fidelity MP3 to telephony-optimized μ-law.","context":15000,"output":15000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/mpeg","audio/wav","audio/pcm","audio/basic","audio/alaw"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-5-turbo","name":"GLM-5-Turbo","lab":"zhipuai","date":"2026-03-16","description":"Faster GLM-5 lane for coding agents that need lower latency","context":200000,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super 120B A12B","lab":"nvidia","date":"2026-03-11","description":"Nemotron middle tier for collaborative agents and high-volume reasoning workloads","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-super-120b-a12b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-embedding-2-preview","name":"Gemini Embedding 2 Preview","lab":"google","date":"2026-03-10","description":"Preview of Gemini Embedding 2, a multimodal embedding model for text, images, video, audio, and PDFs","context":8192,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","audio/mp3","audio/wav","video/mp4","video/mov","application/pdf"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-embedding-2-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4.20-0309-reasoning","name":"Grok 4.20 (Reasoning)","lab":"xai","date":"2026-03-09","description":"Reasoning Grok for document-heavy analysis and long-horizon tool use","context":1000000,"output":30000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.20-0309-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4.20-0309-non-reasoning","name":"Grok 4.20 (Non-Reasoning)","lab":"xai","date":"2026-03-09","description":"Grok model for agentic tool use, reasoning, coding, and live assistance","context":1000000,"output":30000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.20-0309-non-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.4-pro","name":"GPT-5.4 Pro","lab":"openai","date":"2026-03-05","description":"More exact GPT-5.4 tier for demanding professional reasoning and agent tasks","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.4","name":"GPT-5.4","lab":"openai","date":"2026-03-05","description":"Agent-ready GPT for coding and computer-use workflows at a lower cost","context":1050000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4.toml","kind":"model","articles":[{"title":"Introducing GPT-5.4","url":"https://openai.com/index/introducing-gpt-5-4","date":"2026-03-05","published_at":"2026-03-05T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3.1-flash-lite-preview","name":"Gemini 3.1 Flash Lite Preview","lab":"google","date":"2026-03-03","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","lab":"google","date":"2026-03-03","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite.toml","kind":"model","articles":[{"title":"Gemini 3.1 Flash-Lite: Built for intelligence at scale","url":"https://deepmind.google/blog/gemini-3-1-flash-lite-built-for-intelligence-at-scale/","date":"2026-03-03","published_at":"2026-03-03T16:35:55+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3.5-4b","name":"Qwen3.5 4B","lab":"alibaba","date":"2026-03-02","description":"Small Qwen3.5 multimodal model for low-cost chat, reasoning, and tool use","context":262144,"output":81920,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-4b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-2b","name":"Qwen3.5 2B","lab":"alibaba","date":"2026-03-02","description":"Compact Qwen3.5 multimodal model for fast chat, reasoning, and tool use","context":262144,"output":81920,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-2b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-0.8b","name":"Qwen3.5 0.8B","lab":"alibaba","date":"2026-03-02","description":"Smallest Qwen3.5 multimodal model for on-device chat, reasoning, and tool use","context":262144,"output":81920,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-0.8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-moderation-2603","name":"Mistral Moderation 26.03","lab":"mistral","date":"2026-03-01","description":"Moderation classifier for text and conversations with jailbreak detection and multilingual coverage","context":131072,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-moderation-2603.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-9b-base","name":"Qwen3.5 9B Base","lab":"alibaba","date":"2026-02-26","description":"Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-9b-base.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.1-flash-image-preview","name":"Nano Banana 2 Preview","lab":"google","date":"2026-02-26","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":65536,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","application/pdf"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-image-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-35b-a3b-base","name":"Qwen3.5 35B-A3B Base","lab":"alibaba","date":"2026-02-24","description":"Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-35b-a3b-base.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-flash","name":"Qwen3.5 Flash","lab":"alibaba","date":"2026-02-23","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":1000000,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-9b","name":"Qwen3.5 9B","lab":"alibaba","date":"2026-02-23","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-9b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-35b-a3b","name":"Qwen3.5 35B-A3B","lab":"alibaba","date":"2026-02-23","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-35b-a3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-27b","name":"Qwen3.5 27B","lab":"alibaba","date":"2026-02-23","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-27b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-122b-a10b","name":"Qwen3.5 122B-A10B","lab":"alibaba","date":"2026-02-23","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-122b-a10b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime-1.5","name":"GPT-Realtime-1.5","lab":"openai","date":"2026-02-23","description":"Realtime speech-to-speech model for voice agents and customer support","context":32000,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-1.5.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-audio-1.5","name":"GPT-Audio-1.5","lab":"openai","date":"2026-02-23","description":"Audio model for speech input and output with the Chat Completions API","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav","audio/mpeg"],"output_modalities":["text","audio/wav","audio/aac","audio/mpeg","audio/flac","audio/opus","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-audio-1.5.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3.1-pro-preview-customtools","name":"Gemini 3.1 Pro Preview Custom Tools","lab":"google","date":"2026-02-19","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-pro-preview-customtools.toml","kind":"model","articles":[{"title":"Gemini 3.1 Pro: A smarter model for your most complex tasks","url":"https://deepmind.google/blog/gemini-3-1-pro-a-smarter-model-for-your-most-complex-tasks/","date":"2026-02-19","published_at":"2026-02-19T16:06:14+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3.1 Pro"]},{"id":"google/gemini-3.1-pro-preview","name":"Gemini 3.1 Pro Preview","lab":"google","date":"2026-02-19","description":"Reasoning-first Gemini preview for agentic coding and complex problem solving","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-pro-preview.toml","kind":"model","articles":[{"title":"Gemini 3.1 Pro: A smarter model for your most complex tasks","url":"https://deepmind.google/blog/gemini-3-1-pro-a-smarter-model-for-your-most-complex-tasks/","date":"2026-02-19","published_at":"2026-02-19T16:06:14+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3.1 Pro"]},{"id":"anthropic/claude-sonnet-4-6","name":"Claude Sonnet 4.6","lab":"anthropic","date":"2026-02-17","description":"Claude workhorse for coding agents, careful analysis, and production cost control","context":1000000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-6.toml","kind":"model","articles":[{"title":"Released Claude Sonnet 4.6","url":"https://platform.claude.com/docs/en/release-notes/overview#february-17-2026","date":"2026-02-17","published_at":"2026-02-17T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3.5-plus","name":"Qwen3.5 Plus","lab":"alibaba","date":"2026-02-16","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":1000000,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3.5-397b-a17b","name":"Qwen3.5 397B-A17B","lab":"alibaba","date":"2026-02-15","description":"Large open Qwen multimodal MoE for visual agents and long technical tasks","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-397b-a17b.toml","kind":"model","articles":[{"title":"Qwen3.5: Towards Native Multimodal Agents","url":"https://qwen.ai/blog?id=qwen3.5","date":"2026-02-15","published_at":"2026-02-15T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Qwen3.5"]},{"id":"zhipuai/glm-5","name":"GLM-5","lab":"zhipuai","date":"2026-02-12","description":"General GLM flagship for coding, analysis, and tool-heavy engineering workflows","context":204800,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.toml","kind":"model","articles":[{"title":"GLM-5","url":"https://docs.z.ai/release-notes/new-released#2026-02-12","date":"2026-02-12","published_at":"2026-02-12T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-image-2.0","name":"Qwen-Image-2.0","lab":"alibaba","date":"2026-02-10","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-image-2.0","kind":"model","articles":[{"title":"Qwen-Image-2.0: Professional infographics, exquisite photorealism","url":"https://qwen.ai/blog?id=qwen-image-2.0","date":"2026-02-10","published_at":"2026-02-10T05:08:30+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-5.3-codex-spark","name":"GPT-5.3 Codex Spark","lab":"openai","date":"2026-02-05","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","context":128000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.3-codex-spark.toml","kind":"model","articles":[{"title":"Introducing GPT-5.3-Codex-Spark","url":"https://openai.com/index/introducing-gpt-5-3-codex-spark","date":"2026-02-12","published_at":"2026-02-12T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5.3-codex","name":"GPT-5.3 Codex","lab":"openai","date":"2026-02-05","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.3-codex.toml","kind":"model","articles":[{"title":"Introducing GPT-5.3-Codex","url":"https://openai.com/index/introducing-gpt-5-3-codex","date":"2026-02-05","published_at":"2026-02-05T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-6","name":"Claude Opus 4.6","lab":"anthropic","date":"2026-02-05","description":"High-end Claude for difficult coding, planning, and slower expert reasoning","context":1000000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-6.toml","kind":"model","articles":[{"title":"Released Claude Opus 4.6","url":"https://platform.claude.com/docs/en/release-notes/overview#february-5-2026","date":"2026-02-05","published_at":"2026-02-05T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/voxtral-mini-transcribe-realtime-2602","name":"Voxtral Mini Transcribe Realtime","lab":"mistral","date":"2026-02-04","description":"Low-latency streaming speech-to-text model for live transcription and voice agents","context":null,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/voxtral-mini-transcribe-realtime-2602.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/voxtral-mini-2602","name":"Voxtral Mini Transcribe 2","lab":"mistral","date":"2026-02-04","description":"Speech-to-text model with timestamps, optimized for transcription only","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mpeg","audio/flac","audio/ogg","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/voxtral-mini-2602.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-coder-next","name":"Qwen3 Coder Next","lab":"alibaba","date":"2026-02-02","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-next.toml","kind":"model","articles":[{"title":"Qwen3-Coder-Next: Pushing Small Hybrid Models on Agentic Coding","url":"https://qwen.ai/blog?id=qwen3-coder-next","date":"2026-02-02","published_at":"2026-02-02T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-imagine-video","name":"Grok Imagine Video","lab":"xai","date":"2026-01-28","description":"Video model for text-to-video, image-to-video, video editing and extension with native synchronized audio","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp","video/mp4"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-video.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-imagine-image","name":"Grok Imagine Image","lab":"xai","date":"2026-01-28","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":16000,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/jpeg","image/png"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-image.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2.5","name":"Kimi K2.5","lab":"moonshotai","date":"2026-01-27","description":"Earlier Kimi frontier model for long-context agents, coding, and multimodal work","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","image/bmp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.5.toml","kind":"model","articles":[{"title":"Kimi K2.5 Tech Blog: Visual Agentic Intelligence","url":"https://www.kimi.ai/blog/kimi-k2-5","date":null,"published_at":null,"primary":false,"publisher":"moonshotai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-ocr-2","name":"DeepSeek OCR 2","lab":"deepseek","date":"2026-01-27","description":"High-accuracy OCR model for extracting text from documents, screenshots, receipts, and natural scenes","context":8192,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-ocr-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-content-safety-reasoning-4b","name":"Nemotron Content Safety Reasoning 4B","lab":"nvidia","date":"2026-01-22","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-content-safety-reasoning-4b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.7-flashx","name":"GLM-4.7-FlashX","lab":"zhipuai","date":"2026-01-19","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","context":200000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7-flashx.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.7-flash","name":"GLM-4.7-Flash","lab":"zhipuai","date":"2026-01-19","description":"Budget GLM lane for fast coding help, routing, and everyday automation","context":200000,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7-flash.toml","kind":"model","articles":[{"title":"GLM-4.7-Flash","url":"https://docs.z.ai/release-notes/new-released#2026-01-19","date":"2026-01-19","published_at":"2026-01-19T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"zhipuai/glm-image","name":"GLM-Image","lab":"zhipuai","date":"2026-01-14","description":"GLM-Image is an image generation model adopts a hybrid autoregressive + diffusion decoder architecture. In general image generation quality, GLM‑Image aligns with mainstream latent diffusion approaches, but it shows significant advantages in text-rendering and knowledge‑intensive generation scenarios. It performs especially well in tasks requiring precise semantic understanding and complex information expression, while maintaining strong capabilities in high‑fidelity and fine‑grained detail generation. In addition to text‑to‑image generation, GLM‑Image also supports a rich set of image‑to‑image tasks including image editing, style transfer, identity‑preserving generation, and multi‑subject consistency.","context":10240,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-image.toml","kind":"model","articles":[{"title":"GLM-Image","url":"https://docs.z.ai/release-notes/new-released#2026-01-14","date":"2026-01-14","published_at":"2026-01-14T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-reranker","name":"Qwen3-VL-Reranker","lab":"alibaba","date":"2026-01-07","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3-vl-embedding","kind":"model","articles":[{"title":"Qwen3-VL-Embedding and Qwen3-VL-Reranker: For the Next Generation of Multimodal Retrieval","url":"https://qwen.ai/blog?id=qwen3-vl-embedding","date":"2026-01-07","published_at":"2026-01-07T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3-vl-embedding","name":"Qwen3-VL-Embedding","lab":"alibaba","date":"2026-01-07","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3-vl-embedding","kind":"model","articles":[{"title":"Qwen3-VL-Embedding and Qwen3-VL-Reranker: For the Next Generation of Multimodal Retrieval","url":"https://qwen.ai/blog?id=qwen3-vl-embedding","date":"2026-01-07","published_at":"2026-01-07T20:00:00+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-image-2512","name":"Qwen-Image-2512","lab":"alibaba","date":"2025-12-31","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-image-2512","kind":"model","articles":[{"title":"Qwen-Image-2512: Finer Details, Greater Realism","url":"https://qwen.ai/blog?id=qwen-image-2512","date":"2025-12-31","published_at":"2025-12-31T05:08:30+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-image-edit-2511","name":"Qwen-Image-Edit-2511","lab":"alibaba","date":"2025-12-23","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-image-edit-2511","kind":"model","articles":[{"title":"Qwen-Image-Edit-2511: Improve Consistency","url":"https://qwen.ai/blog?id=qwen-image-edit-2511","date":"2025-12-23","published_at":"2025-12-23T05:08:30+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen3-tts","name":"Qwen3-TTS","lab":"alibaba","date":"2025-12-22","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen3-tts-vc-voicedesign","kind":"model","articles":[{"title":"Qwen3-TTS Steps Up: Voice Cloning and Voice Design!","url":"https://qwen.ai/blog?id=qwen3-tts-vc-voicedesign","date":"2025-12-22","published_at":"2025-12-22T16:00:45+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"zhipuai/glm-4.7","name":"GLM-4.7","lab":"zhipuai","date":"2025-12-22","description":"Mature GLM model for dependable coding, reasoning, and structured agent tasks","context":204800,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7.toml","kind":"model","articles":[{"title":"GLM-4.7","url":"https://docs.z.ai/release-notes/new-released#2025-12-22","date":"2025-12-22","published_at":"2025-12-22T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-image-layered","name":"Qwen-Image-Layered","lab":"alibaba","date":"2025-12-19","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://qwen.ai/blog?id=qwen-image-layered","kind":"model","articles":[{"title":"Qwen-Image-Layered: Layered Decomposition for Inherent Editablity","url":"https://qwen.ai/blog?id=qwen-image-layered","date":"2025-12-19","published_at":"2025-12-19T05:08:30+00:00","primary":true,"publisher":"alibaba","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-4-fast-reasoning","name":"X-Ai/Grok-4-Fast-Reasoning","lab":"xai","date":"2025-12-18","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","context":2000000,"output":2000000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","audio","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4-fast-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4-fast-non-reasoning","name":"X-Ai/Grok-4-Fast-Non-Reasoning","lab":"xai","date":"2025-12-18","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","context":2000000,"output":2000000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","audio","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4-fast-non-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"Llama Nemotron Rerank VL 1B v2","lab":"nvidia","date":"2025-12-18","description":"Reranking model for improving retrieval quality in search and recommendation systems","context":10240,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif","image/bmp","image/tiff"],"output_modalities":["reranking"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-nemotron-rerank-vl-1b-v2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"Llama Nemotron Embed VL 1B v2","lab":"nvidia","date":"2025-12-18","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","context":10240,"output":2048,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-nemotron-embed-vl-1b-v2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-ocr-2512","name":"Mistral OCR 3","lab":"mistral","date":"2025-12-17","description":"Document OCR model that extracts interleaved text and images from documents","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["image/jpeg","image/png","image/avif","image/tiff","image/gif","image/heic","image/heif","image/bmp","image/webp","application/pdf","text/csv","text/plain","text/xml","text/troff"],"output_modalities":["text","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-ocr-2512.toml","kind":"model","articles":[{"title":"Introducing Mistral OCR 3","url":"https://mistral.ai/news/mistral-ocr-3/","date":"2025-12-17","published_at":"2025-12-17T15:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemini-3-flash-preview","name":"Gemini 3 Flash Preview","lab":"google","date":"2025-12-17","description":"New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-flash-preview.toml","kind":"model","articles":[{"title":"Gemini 3 Flash: frontier intelligence built for speed","url":"https://deepmind.google/blog/gemini-3-flash-frontier-intelligence-built-for-speed/","date":"2025-12-17","published_at":"2025-12-17T11:58:17+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3 Flash"]},{"id":"nvidia/nemotron-3-nano-30b-a3b","name":"Nemotron 3 Nano 30B A3B","lab":"nvidia","date":"2025-12-15","description":"Small Nemotron 3 MoE for efficient coding, math, and long-context agents","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-nano-30b-a3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-native-audio-preview-12-2025","name":"Gemini 2.5 Flash Native Audio Preview 12-2025","lab":"google","date":"2025-12-12","description":"Gemini 2.5 Flash Live API model with native audio for real-time conversational agents","context":131072,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video","audio/pcm"],"output_modalities":["text","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-native-audio-preview-12-2025.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.2-pro","name":"GPT-5.2 Pro","lab":"openai","date":"2025-12-11","description":"Higher-accuracy GPT-5.2 variant for tougher reasoning and review workflows","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.2-codex","name":"GPT-5.2 Codex","lab":"openai","date":"2025-12-11","description":"Code-specialist GPT for repository edits, reviews, and long-running software agents","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2-codex.toml","kind":"model","articles":[{"title":"Introducing GPT-5.2-Codex","url":"https://openai.com/index/introducing-gpt-5-2-codex","date":"2025-12-18","published_at":"2025-12-18T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5.2","name":"GPT-5.2","lab":"openai","date":"2025-12-11","description":"Reliable GPT generation for broad coding, writing, and tool-assisted product work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2.toml","kind":"model","articles":[{"title":"Introducing GPT-5.2","url":"https://openai.com/index/introducing-gpt-5-2","date":"2025-12-11","published_at":"2025-12-11T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"zhipuai/glm-asr-2512","name":"GLM-ASR-2512","lab":"zhipuai","date":"2025-12-10","description":"Speech recognition model for multilingual and dialect transcription with custom hotwords","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-asr-2512.toml","kind":"model","articles":[{"title":"GLM-ASR-2512","url":"https://docs.z.ai/release-notes/new-released#2025-12-10","date":"2025-12-10","published_at":"2025-12-10T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"zhipuai/autoglm-phone-9b-multilingual","name":"AutoGLM Phone 9B Multilingual","lab":"zhipuai","date":"2025-12-10","description":"Multilingual visual model for operating smartphone interfaces and mobile agents","context":65536,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/autoglm-phone-9b-multilingual.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/devstral-small-2","name":"Devstral Small 2","lab":"mistral","date":"2025-12-09","description":"Compact multimodal coding model for repository exploration, file editing, and software agents","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-small-2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/devstral-2512","name":"Devstral 2","lab":"mistral","date":"2025-12-09","description":"Mistral's coding-agent model for repository work, terminal tasks, and software fixes","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-2512.toml","kind":"model","articles":[{"title":"Introducing: Devstral 2 and Mistral Vibe CLI.","url":"https://mistral.ai/news/devstral-2-vibe-cli/","date":"2025-12-09","published_at":"2025-12-09T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"zhipuai/glm-4.6v-flash","name":"GLM-4.6V-Flash","lab":"zhipuai","date":"2025-12-08","description":"Lightweight GLM vision model for visual reasoning, documents, and multimodal agents","context":128000,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","video/x-matroska","video/quicktime"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6v-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.6v","name":"GLM-4.6V","lab":"zhipuai","date":"2025-12-08","description":"GLM vision model for visual reasoning, documents, and multimodal agents","context":128000,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","video/x-matroska","video/quicktime"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6v.toml","kind":"model","articles":[{"title":"GLM-4.6V","url":"https://docs.z.ai/release-notes/new-released#2025-12-08","date":"2025-12-08","published_at":"2025-12-08T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/wan2.6","name":"Wan2.6","lab":"alibaba","date":"2025-12-03","description":"Video model for text- and image-to-video with audio input and synchronized sound","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/bmp","image/webp","audio/wav","audio/mpeg"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/wan2.6.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","lab":"mistral","date":"2025-12-02","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-8b-2512","name":"Ministral 3 8B 2512","lab":"mistral","date":"2025-12-02","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","context":262144,"output":209715,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-8b-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-3-8b-instruct-2512","name":"Ministral 3 8B","lab":"mistral","date":"2025-12-02","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3-8b-instruct-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-3b-2512","name":"Ministral 3 3B 2512","lab":"mistral","date":"2025-12-02","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","context":131072,"output":104857,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3b-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-3-3b-instruct-2512","name":"Ministral 3 3B","lab":"mistral","date":"2025-12-02","description":"Compact open vision-language model for edge deployment, instruction following, and tool use","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3-3b-instruct-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-14b-2512","name":"Ministral 3 14B 2512","lab":"mistral","date":"2025-12-02","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","context":262144,"output":209715,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-14b-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-3-14b-instruct-2512","name":"Ministral 3 14B","lab":"mistral","date":"2025-12-02","description":"Open vision-language model for efficient local deployment, instruction following, and tool use","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3-14b-instruct-2512.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-14b","name":"Ministral 14B","lab":"mistral","date":"2025-12-02","description":"Compact multimodal Mistral model for local assistants, edge agents, and efficient tool use","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-14b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v3.2","name":"DeepSeek V3.2","lab":"deepseek","date":"2025-12-01","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes, sparse attention, and tool-use","context":128000,"output":64000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.2.toml","kind":"model","articles":[{"title":"DeepSeek-V3.2 Release","url":"https://api-docs.deepseek.com/news/news251201","date":"2025-12-01","published_at":"2025-12-01T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-image-1.5","name":"GPT-Image-1.5","lab":"openai","date":"2025-11-25","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["text","image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-1.5.toml","kind":"model","articles":[{"title":"Introducing ChatGPT Images and GPT‑Image‑1.5","url":"https://openai.com/index/new-chatgpt-images-is-here","date":"2025-12-16","published_at":"2025-12-16T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-5","name":"Claude Opus 4.5","lab":"anthropic","date":"2025-11-24","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","context":200000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-5.toml","kind":"model","articles":[{"title":"Released Claude Opus 4.5","url":"https://platform.claude.com/docs/en/release-notes/overview#november-24-2025","date":"2025-11-24","published_at":"2025-11-24T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-3-pro-image-preview","name":"Nano Banana Pro Preview","lab":"google","date":"2025-11-20","description":"Nano Banana Pro for higher-fidelity image generation and design-heavy edits","context":65536,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-image-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4.1-fast-reasoning","name":"Grok 4.1 Fast (Reasoning)","lab":"xai","date":"2025-11-19","description":"xAI's fast agentic tool-calling model with a 2M context window and built-in reasoning","context":2000000,"output":30000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.1-fast-reasoning.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4.1-fast","name":"Grok 4.1 Fast","lab":"xai","date":"2025-11-19","description":"xAI's fast agentic tool-calling model with a 2M context window; non-reasoning variant for low-latency responses","context":2000000,"output":30000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.1-fast.toml","kind":"model","articles":[{"title":"Grok 4.1 Fast and Agent Tools API","url":"https://x.ai/news/grok-4-1-fast","date":"2025-11-19","published_at":"2025-11-19T00:00:00+00:00","primary":false,"publisher":"xai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-3-pro-preview","name":"Gemini 3 Pro Preview","lab":"google","date":"2025-11-18","description":"Preview Gemini flagship for complex reasoning, coding, and rich multimodal prompts","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-preview.toml","kind":"model","articles":[{"title":"A new era of intelligence with Gemini 3","url":"https://deepmind.google/blog/a-new-era-of-intelligence-with-gemini-3/","date":"2025-11-18","published_at":"2025-11-18T16:06:41+00:00","primary":true,"publisher":"google","also":[]},{"title":"Start building with Gemini 3","url":"https://deepmind.google/blog/start-building-with-gemini-3/","date":"2025-11-18","published_at":"2025-11-18T17:49:13+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Gemini 3"]},{"id":"xai/grok-4.1","name":"Grok 4.1","lab":"xai","date":"2025-11-17","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-4-1","kind":"model","articles":[{"title":"Grok 4.1","url":"https://x.ai/news/grok-4-1","date":"2025-11-17","published_at":"2025-11-17T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-5.1-codex-mini","name":"GPT-5.1 Codex mini","lab":"openai","date":"2025-11-13","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.1-codex-max","name":"GPT-5.1 Codex Max","lab":"openai","date":"2025-11-13","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex-max.toml","kind":"model","articles":[{"title":"Building more with GPT-5.1-Codex-Max","url":"https://openai.com/index/gpt-5-1-codex-max","date":"2025-11-19","published_at":"2025-11-19T00:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5.1-codex","name":"GPT-5.1 Codex","lab":"openai","date":"2025-11-13","description":"Codex GPT for repository edits, code review, and practical software agents","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5.1","name":"GPT-5.1","lab":"openai","date":"2025-11-13","description":"Sharper GPT-5 generation for coding, product work, and tool-assisted tasks","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1.toml","kind":"model","articles":[{"title":"Introducing GPT-5.1 for developers","url":"https://openai.com/index/gpt-5-1-for-developers","date":"2025-11-13","published_at":"2025-11-13T00:00:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"GPT-5.1: A smarter, more conversational ChatGPT","url":"https://openai.com/index/gpt-5-1","date":"2025-11-12","published_at":"2025-11-12T00:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"moonshotai/kimi-k2-thinking-turbo","name":"Kimi K2 Thinking Turbo","lab":"moonshotai","date":"2025-11-06","description":"Kimi reasoning model for long-horizon research, planning, and tool use","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-thinking-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2-thinking","name":"Kimi K2 Thinking","lab":"moonshotai","date":"2025-11-06","description":"Thinking Kimi model for slower research passes, planning, and hard technical questions","context":262144,"output":262144,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-thinking.toml","kind":"model","articles":[{"title":"Kimi K2 Thinking","url":"https://www.kimi.ai/blog/kimi-k2-thinking","date":null,"published_at":null,"primary":false,"publisher":"moonshotai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-oss-safeguard-20b","name":"GPT OSS Safeguard 20B","lab":"openai","date":"2025-10-29","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-safeguard-20b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-oss-safeguard-120b","name":"GPT OSS Safeguard 120B","lab":"openai","date":"2025-10-29","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-safeguard-120b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/nemotron-nano-12b-v2-vl","name":"Nemotron Nano 12B v2 VL","lab":"nvidia","date":"2025-10-28","description":"Nemotron multimodal model for visual reasoning and agentic AI workflows","context":128000,"output":128000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","video/mp4","video/x-matroska","video/x-flv","video/3gpp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-nano-12b-v2-vl.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-3.1-nemotron-safety-guard-8b-v3","name":"Llama 3.1 Nemotron Safety Guard 8B v3","lab":"nvidia","date":"2025-10-28","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.1-nemotron-safety-guard-8b-v3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-3n","name":"Gemma 3n","lab":"google","date":"2025-10-25","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://deepmind.google/blog/introducing-gemma-3n-the-developer-guide/","kind":"model","articles":[{"title":"Introducing Gemma 3n: The developer guide","url":"https://deepmind.google/blog/introducing-gemma-3n-the-developer-guide/","date":"2025-10-25","published_at":"2025-10-25T17:54:47+00:00","primary":true,"publisher":"google","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-4o-transcribe-diarize","name":"GPT-4o Transcribe Diarize","lab":"openai","date":"2025-10-17","description":"Speech-to-text model with built-in speaker diarization","context":16000,"output":2000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-transcribe-diarize.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-nemotron-embed-1b-v2","name":"Llama Nemotron Embed 1B v2","lab":"nvidia","date":"2025-10-16","description":"Multilingual text embedding model for retrieval and question answering pipelines","context":8192,"output":2048,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-nemotron-embed-1b-v2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5-image-mini","name":"GPT-5 Image Mini","lab":"openai","date":"2025-10-16","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["application/pdf","image/jpeg","image/png","image/gif","image/webp","text"],"output_modalities":["image/png","image/jpeg","image/webp","text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-image-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/veo-3.1-generate-preview","name":"Veo 3.1 Preview","lab":"google","date":"2025-10-15","description":"Video model for prompt-guided generation, editing, and motion workflows","context":1024,"output":1,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-generate-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/veo-3.1-fast-generate-preview","name":"Veo 3.1 Fast Preview","lab":"google","date":"2025-10-15","description":"Video model for prompt-guided generation, editing, and motion workflows","context":1024,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-fast-generate-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-flash","name":"Qwen3 VL Flash (Alibaba Cloud)","lab":"alibaba","date":"2025-10-15","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-haiku-4-5","name":"Claude Haiku 4.5","lab":"anthropic","date":"2025-10-15","description":"Fast Claude lane for lightweight agents, office tasks, and responsive chat","context":200000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-haiku-4-5.toml","kind":"model","articles":[{"title":"Released Claude Haiku 4.5","url":"https://platform.claude.com/docs/en/release-notes/overview#october-15-2025","date":"2025-10-15","published_at":"2025-10-15T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5-search-api","name":"GPT-5 Search API","lab":"openai","date":"2025-10-14","description":"GPT-5 model trained for web search in the Chat Completions API","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-search-api.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5-image","name":"GPT-5 Image","lab":"openai","date":"2025-10-14","description":"Image model for prompt-driven generation, editing, and visual design workflows","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["image/jpeg","image/png","image/gif","image/webp","text","application/pdf"],"output_modalities":["image/png","image/jpeg","image/webp","text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-image.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-computer-use-preview-10-2025","name":"Gemini 2.5 Computer Use Preview","lab":"google","date":"2025-10-07","description":"Specialized Gemini 2.5 model for browser-control agents that automate UI tasks","context":128000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-computer-use-preview-10-2025.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime-mini","name":"GPT-Realtime Mini","lab":"openai","date":"2025-10-06","description":"Cost-efficient realtime speech-to-speech model for voice agents","context":32000,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-image-1-mini","name":"GPT-Image-1 Mini","lab":"openai","date":"2025-10-06","description":"Cost-efficient GPT Image 1 variant for image generation and editing","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-1-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-audio-mini","name":"GPT-Audio Mini","lab":"openai","date":"2025-10-06","description":"Cost-efficient audio model for speech input and output with the Chat Completions API","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav","audio/mpeg"],"output_modalities":["text","audio/wav","audio/aac","audio/mpeg","audio/flac","audio/opus","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-audio-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5-pro","name":"GPT-5 Pro","lab":"openai","date":"2025-10-06","description":"Higher-accuracy GPT-5 tier for tough analysis, coding reviews, and planning","context":400000,"output":272000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-30b-a3b-instruct","name":"Qwen3 VL 30B A3B Instruct","lab":"alibaba","date":"2025-10-04","description":"Open vision-language MoE model for image and video understanding, documents, and visual agents","context":262144,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-30b-a3b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-pro-tts","name":"Gemini 2.5 Pro TTS","lab":"google","date":"2025-09-30","description":"Speech generation model for controllable voice, narration, and audio delivery","context":32768,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/l16"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-pro-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-tts","name":"Gemini 2.5 Flash TTS","lab":"google","date":"2025-09-30","description":"Speech generation model for controllable voice, narration, and audio delivery","context":32768,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/l16"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.6","name":"GLM-4.6","lab":"zhipuai","date":"2025-09-30","description":"Late GLM-4 workhorse for coding agents, reasoning, and structured tasks","context":204800,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6.toml","kind":"model","articles":[{"title":"GLM-4.6","url":"https://docs.z.ai/release-notes/new-released#2025-09-30","date":"2025-09-30","published_at":"2025-09-30T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-v3.2-exp","name":"DeepSeek-V3.2-Exp","lab":"deepseek","date":"2025-09-29","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://api-docs.deepseek.com/news/news250929","kind":"model","articles":[{"title":"Introducing DeepSeek-V3.2-Exp","url":"https://api-docs.deepseek.com/news/news250929","date":"2025-09-29","published_at":"2025-09-29T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"official"},{"id":"anthropic/claude-sonnet-4-5","name":"Claude Sonnet 4.5","lab":"anthropic","date":"2025-09-29","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","context":200000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-5.toml","kind":"model","articles":[{"title":"Released Claude Sonnet 4.5","url":"https://platform.claude.com/docs/en/release-notes/overview#september-29-2025","date":"2025-09-29","published_at":"2025-09-29T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-lite-preview-09-2025","name":"Gemini 2.5 Flash-Lite Preview 09-2025","lab":"google","date":"2025-09-25","description":"September 2025 preview of Gemini 2.5 Flash-Lite with better instruction following and multimodal quality","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-lite-preview-09-2025.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-plus","name":"Qwen3-VL Plus","lab":"alibaba","date":"2025-09-23","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":262144,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-235b-a22b-thinking","name":"Qwen3 VL 235B A22B Thinking","lab":"alibaba","date":"2025-09-23","description":"Qwen vision-language thinking model for visual reasoning, documents, and agent tasks","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-235b-a22b-thinking.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-vl-235b-a22b-instruct","name":"Qwen3 VL 235B A22B Instruct","lab":"alibaba","date":"2025-09-23","description":"Qwen vision-language instruct model for visual reasoning, documents, and agent tasks","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-235b-a22b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-max","name":"Qwen3 Max","lab":"alibaba","date":"2025-09-23","description":"Flagship Qwen3 model for coding agents, complex reasoning, and tool use","context":262144,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-max.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-omni-30b-a3b-thinking","name":"Qwen3 Omni 30B A3B Thinking","lab":"alibaba","date":"2025-09-22","description":"Multimodal reasoning model accepting text, images, video, and audio with text output","context":65536,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv","audio/amr","audio/wav","audio/3gpp","audio/aac","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-omni-30b-a3b-thinking.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v3.1-terminus","name":"DeepSeek-V3.1-Terminus","lab":"deepseek","date":"2025-09-22","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://api-docs.deepseek.com/news/news250922","kind":"model","articles":[{"title":"DeepSeek-V3.1-Terminus","url":"https://api-docs.deepseek.com/news/news250922","date":"2025-09-22","published_at":"2025-09-22T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-4-fast","name":"Grok 4 Fast","lab":"xai","date":"2025-09-19","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-4-fast","kind":"model","articles":[{"title":"Grok 4 Fast","url":"https://x.ai/news/grok-4-fast","date":"2025-09-19","published_at":"2025-09-19T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"mistral/magistral-small-2509","name":"Magistral Small 1.2","lab":"mistral","date":"2025-09-18","description":"Open multimodal reasoning model for transparent analysis of text and images","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/magistral-small-2509.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5-codex","name":"GPT-5-Codex","lab":"openai","date":"2025-09-15","description":"Coding-optimized GPT model for repository edits, reviews, and agentic software work","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-codex.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-max-preview","name":"Qwen3 Max Preview","lab":"alibaba","date":"2025-09-05","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","context":262144,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-max-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2-0905","name":"Kimi K2 Instruct 0905","lab":"moonshotai","date":"2025-09-05","description":"September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding","context":262144,"output":98304,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-0905.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-code-fast-1","name":"x-AI/Grok-Code-Fast 1","lab":"xai","date":"2025-09-02","description":"Fast Grok model for responsive chat, reasoning, and tool-assisted work","context":256000,"output":10000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-code-fast-1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/chirp-3","name":"Chirp 3","lab":"google","date":"2025-08-29","description":"Multilingual speech-to-text model with diarization and automatic language detection","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["audio/wav","audio/mpeg","audio/flac","audio/mp4","audio/ogg","audio/webm","audio/aac"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/chirp-3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-realtime","name":"GPT-Realtime","lab":"openai","date":"2025-08-28","description":"Realtime speech-to-speech model for low-latency voice agents over WebRTC, WebSocket, or SIP","context":32000,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/pcm","audio/pcmu","audio/pcma","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text","audio/pcm","audio/pcmu","audio/pcma"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime.toml","kind":"model","articles":[{"title":"Introducing gpt-realtime and Realtime API updates","url":"https://openai.com/index/introducing-gpt-realtime","date":"2025-08-28","published_at":"2025-08-28T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-audio","name":"GPT-Audio","lab":"openai","date":"2025-08-28","description":"Audio model for speech input and output with the Chat Completions API","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav","audio/mpeg"],"output_modalities":["text","audio/wav","audio/aac","audio/mpeg","audio/flac","audio/opus","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-audio.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-image","name":"Nano Banana","lab":"google","date":"2025-08-26","description":"Nano Banana image model for fast generation, edits, and character-consistent assets","context":32768,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text","image/png","image/jpeg"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-image.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v3.1","name":"DeepSeek-V3.1","lab":"deepseek","date":"2025-08-21","description":"Hybrid-reasoning DeepSeek model with thinking and non-thinking modes","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.1.toml","kind":"model","articles":[{"title":"DeepSeek-V3.1 Release","url":"https://api-docs.deepseek.com/news/news250821","date":"2025-08-21","published_at":"2025-08-21T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"deepseek/deepseek-chat-v3.1","name":"DeepSeek V3.1","lab":"deepseek","date":"2025-08-21","description":"DeepSeek chat model for instruction following, coding, and analysis","context":163840,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-chat-v3.1.toml","kind":"model","articles":[{"title":"DeepSeek-V3.1 Release","url":"https://api-docs.deepseek.com/news/news250821","date":"2025-08-21","published_at":"2025-08-21T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/nemotron-nano-9b-v2","name":"Nemotron Nano 9B v2","lab":"nvidia","date":"2025-08-18","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-nano-9b-v2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-medium-3.1","name":"Mistral Medium 3.1","lab":"mistral","date":"2025-08-12","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":131072,"output":104857,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-3.1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.5v","name":"GLM-4.5V","lab":"zhipuai","date":"2025-08-11","description":"GLM vision model for visual reasoning, documents, and multimodal agents","context":64000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","video/mp4","video/x-matroska","video/quicktime"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5v.toml","kind":"model","articles":[{"title":"GLM-4.5V","url":"https://docs.z.ai/release-notes/new-released#2025-08-11","date":"2025-08-11","published_at":"2025-08-11T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-5-nano","name":"GPT-5 Nano","lab":"openai","date":"2025-08-07","description":"Tiny GPT-5 lane for routing, extraction, classification, and bulk jobs","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-nano.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5-mini","name":"GPT-5 Mini","lab":"openai","date":"2025-08-07","description":"Small GPT-5 for responsive agents, coding help, and everyday automation","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-5","name":"GPT-5","lab":"openai","date":"2025-08-07","description":"Original GPT-5 workhorse for reasoning, coding, writing, and tool workflows","context":400000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.toml","kind":"model","articles":[{"title":"GPT-5: Our best model for work","url":"https://openai.com/business/learn/gpt-5-our-best-model-for-work","date":"2025-08-07","published_at":"2025-08-07T00:00:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"Introducing GPT-5","url":"https://openai.com/index/introducing-gpt-5","date":"2025-08-07","published_at":"2025-08-07T00:00:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"Introducing GPT-5 for developers","url":"https://openai.com/index/introducing-gpt-5-for-developers","date":"2025-08-07","published_at":"2025-08-07T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","lab":"openai","date":"2025-08-05","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-20b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-oss-120b","name":"GPT OSS 120B","lab":"openai","date":"2025-08-05","description":"Open GPT reasoning model for self-hosted agents and controllable deployments","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-120b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-1","name":"Claude Opus 4.1","lab":"anthropic","date":"2025-08-05","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","context":200000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-1.toml","kind":"model","articles":[{"title":"Released Claude Opus 4.1","url":"https://platform.claude.com/docs/en/release-notes/overview#august-5-2025","date":"2025-08-05","published_at":"2025-08-05T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3-coder-30b-a3b-instruct","name":"Qwen3-Coder 30B-A3B Instruct","lab":"alibaba","date":"2025-07-31","description":"Smaller Qwen coder for efficient local agents and repo-level fixes","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-30b-a3b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/codestral-2508","name":"Codestral 25.08","lab":"mistral","date":"2025-07-30","description":"Mistral code model for low-latency completion, fill-in-the-middle, and code generation","context":128000,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/codestral-2508.toml","kind":"model","articles":[{"title":"Announcing Codestral 25.08 and the Complete Mistral Coding Stack for Enterprise","url":"https://mistral.ai/news/codestral-25-08/","date":"2025-07-30","published_at":"2025-07-30T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3-coder-flash","name":"Qwen3 Coder Flash","lab":"alibaba","date":"2025-07-28","description":"Qwen coding model for software agents, repository edits, and code reasoning","context":1000000,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-30b-a3b-instruct-2507","name":"Qwen3 30B-A3B Instruct 2507","lab":"alibaba","date":"2025-07-28","description":"Updated compact Qwen3 MoE instruct model for multilingual chat, coding, and tool use","context":262144,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-30b-a3b-instruct-2507.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-flash","name":"Qwen Flash","lab":"alibaba","date":"2025-07-28","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","context":1000000,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.5-flash","name":"GLM-4.5-Flash","lab":"zhipuai","date":"2025-07-28","description":"Efficient GLM model for fast reasoning, coding, and agent workflows","context":131072,"output":98304,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.5-air","name":"GLM-4.5-Air","lab":"zhipuai","date":"2025-07-28","description":"Lighter GLM-4.5 variant for fast coding assistance and cheaper agents","context":131072,"output":98304,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5-air.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"zhipuai/glm-4.5","name":"GLM-4.5","lab":"zhipuai","date":"2025-07-28","description":"Hybrid-reasoning GLM release that made the 4.5 line broadly useful","context":131072,"output":98304,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5.toml","kind":"model","articles":[{"title":"GLM-4.5 Series","url":"https://docs.z.ai/release-notes/new-released#2025-07-28","date":"2025-07-28","published_at":"2025-07-28T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen3-235b-a22b-thinking-2507","name":"Qwen3 235B-A22B Thinking 2507","lab":"alibaba","date":"2025-07-25","description":"Updated large open Qwen3 MoE thinking model for reasoning, math, coding, and tool use","context":262144,"output":81920,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-235b-a22b-thinking-2507.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1.5","name":"Llama 3.3 Nemotron Super 49B v1.5","lab":"nvidia","date":"2025-07-25","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.3-nemotron-super-49b-v1.5.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-mt-plus","name":"Qwen MT Plus","lab":"alibaba","date":"2025-07-24","description":"Flagship Qwen translation model with terminology control and support for 92 languages","context":16384,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-mt-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-coder-plus","name":"Qwen3 Coder Plus","lab":"alibaba","date":"2025-07-23","description":"Hosted Qwen coder for software agents, repo edits, and long-context code","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-coder-480b-a35b-instruct","name":"Qwen3-Coder 480B-A35B Instruct","lab":"alibaba","date":"2025-07-22","description":"Open Qwen coding heavyweight for repository reasoning and agentic engineering","context":262144,"output":65536,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-480b-a35b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-235b-a22b-instruct-2507","name":"Qwen3 235B-A22B Instruct 2507","lab":"alibaba","date":"2025-07-21","description":"Updated large open Qwen3 MoE instruct model for multilingual chat, coding, and tool use","context":262144,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-235b-a22b-instruct-2507.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/voxtral-small-24b-2507","name":"Voxtral Small 24B 2507","lab":"mistral","date":"2025-07-15","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/voxtral-small-24b-2507.toml","kind":"model","articles":[{"title":"Voxtral","url":"https://mistral.ai/news/voxtral/","date":"2025-07-15","published_at":"2025-07-15T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]},{"title":"Voxtral transcribes at the speed of sound.","url":"https://mistral.ai/news/voxtral-transcribe-2/","date":"2026-02-04","published_at":"2026-02-04T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]},{"title":"Speaking of Voxtral","url":"https://mistral.ai/news/voxtral-tts/","date":"2026-03-23","published_at":"2026-03-23T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Voxtral"]},{"id":"mistral/voxtral-mini-3b-2507","name":"Voxtral Mini 3B 2507","lab":"mistral","date":"2025-07-15","description":"Open audio-language model for speech transcription, audio understanding, and voice-driven tool use","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","audio/wav","audio/mpeg"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/voxtral-mini-3b-2507.toml","kind":"model","articles":[{"title":"Voxtral","url":"https://mistral.ai/news/voxtral/","date":"2025-07-15","published_at":"2025-07-15T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]},{"title":"Voxtral transcribes at the speed of sound.","url":"https://mistral.ai/news/voxtral-transcribe-2/","date":"2026-02-04","published_at":"2026-02-04T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]},{"title":"Speaking of Voxtral","url":"https://mistral.ai/news/voxtral-tts/","date":"2026-03-23","published_at":"2026-03-23T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Voxtral"]},{"id":"zhipuai/cogvideox-3","name":"CogVideoX-3","lab":"zhipuai","date":"2025-07-15","description":"Video generation model for text-to-video, image-to-video, and first/last-frame clips with optional sound effects","context":512,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg"],"output_modalities":["video/mp4"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/cogvideox-3.toml","kind":"model","articles":[{"title":"CogVideoX-3","url":"https://docs.z.ai/release-notes/new-released#2025-07-15","date":"2025-07-15","published_at":"2025-07-15T00:00:00+00:00","primary":true,"publisher":"zhipuai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"moonshotai/kimi-k2-instruct","name":"Kimi K2 Instruct","lab":"moonshotai","date":"2025-07-11","description":"Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"moonshotai/kimi-k2","name":"Kimi K2 0711","lab":"moonshotai","date":"2025-07-11","description":"Kimi model for long-context chat, coding, and agentic reasoning","context":131072,"output":98304,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/devstral-small-2507","name":"Devstral Small","lab":"mistral","date":"2025-07-10","description":"Mistral coding agent model for repository tasks and software engineering workflows","context":128000,"output":128000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-small-2507.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/devstral-medium-2507","name":"Devstral Medium","lab":"mistral","date":"2025-07-10","description":"Mistral coding agent model for repository tasks and software engineering workflows","context":128000,"output":128000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-medium-2507.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-4","name":"Grok 4","lab":"xai","date":"2025-07-09","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-4","kind":"model","articles":[{"title":"Grok 4","url":"https://x.ai/news/grok-4","date":"2025-07-09","published_at":"2025-07-09T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/o4-mini-deep-research","name":"o4-mini-deep-research","lab":"openai","date":"2025-06-26","description":"Research model for long-horizon investigation, synthesis, and analytical reports","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o4-mini-deep-research.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/o3-deep-research","name":"o3-deep-research","lab":"openai","date":"2025-06-26","description":"Research model for long-horizon investigation, synthesis, and analytical reports","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-deep-research.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-3n-e4b-it","name":"Gemma 3n E4B IT","lab":"google","date":"2025-06-26","description":"Efficient on-device Gemma 3n model for text, image, and audio understanding","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3n-e4b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-3n-e2b-it","name":"Gemma 3n E2B IT","lab":"google","date":"2025-06-26","description":"Efficient on-device Gemma 3n model for text, image, and audio understanding","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3n-e2b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-small-3.2-24b-instruct","name":"Mistral Small 3.2 24B","lab":"mistral","date":"2025-06-20","description":"Efficient Mistral model for fast chat, extraction, and production assistants","context":256000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["image/png","image/jpeg","image/webp","image/gif","text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-3.2-24b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-small-2506","name":"Mistral Small 3.2","lab":"mistral","date":"2025-06-20","description":"Efficient Mistral model for fast chat, extraction, and production assistants","context":128000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-2506.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-pro","name":"Gemini 2.5 Pro","lab":"google","date":"2025-06-17","description":"Google's proven reasoning model for coding, math, and multimodal analysis","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-lite-preview-06-17","name":"Gemini 2.5 Flash-Lite Preview 06-17","lab":"google","date":"2025-06-17","description":"First preview of Gemini 2.5 Flash-Lite, the low-cost, low-latency 2.5 model","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-lite-preview-06-17.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-lite","name":"Gemini 2.5 Flash-Lite","lab":"google","date":"2025-06-17","description":"Lean Gemini 2.5 lane for cheap multimodal traffic and quick agents","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-lite.toml","kind":"model","articles":[{"title":"Gemini 2.5 Flash-Lite is now ready for scaled production use","url":"https://deepmind.google/blog/gemini-25-flash-lite-is-now-ready-for-scaled-production-use/","date":"2025-10-25","published_at":"2025-10-25T17:34:32+00:00","primary":false,"publisher":"google","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash","name":"Gemini 2.5 Flash","lab":"google","date":"2025-06-17","description":"Fast Gemini workhorse for multimodal apps where latency and price matter","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/mistral-nemotron","name":"Mistral Nemotron","lab":"nvidia","date":"2025-06-11","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":128000,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/mistral-nemotron.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/o3-pro","name":"o3-pro","lab":"openai","date":"2025-06-10","description":"High-effort o3 tier for difficult technical reasoning and careful answers","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/magistral-small-2506","name":"Magistral Small","lab":"mistral","date":"2025-06-10","description":"Open Mistral reasoning model for transparent step-by-step problem solving","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/magistral-small-2506.toml","kind":"model","articles":[{"title":"Magistral","url":"https://mistral.ai/news/magistral/","date":"2025-06-10","published_at":"2025-06-10T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Magistral"]},{"id":"alibaba/qwen3-reranker-8b","name":"Qwen3 Reranker 8B","lab":"alibaba","date":"2025-06-05","description":"Multilingual query-document reranking model supporting more than 100 languages","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["reranking"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-reranker-8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-reranker-0.6b","name":"Qwen3 Reranker 0.6B","lab":"alibaba","date":"2025-06-05","description":"Compact multilingual query-document reranking model supporting more than 100 languages","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["reranking"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-reranker-0.6b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-embedding-8b","name":"Qwen3 Embedding 8B","lab":"alibaba","date":"2025-06-05","description":"Multilingual text embedding model for retrieval, code search, classification, and clustering","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-embedding-8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-embedding-4b","name":"Qwen3 Embedding 4B","lab":"alibaba","date":"2025-06-05","description":"Multilingual text embedding model for retrieval, code search, classification, and clustering","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-embedding-4b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-embedding-0.6b","name":"Qwen3 Embedding 0.6B","lab":"alibaba","date":"2025-06-05","description":"Compact multilingual text embedding model for retrieval, code search, classification, and clustering","context":32768,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-embedding-0.6b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-pro-preview","name":"Gemini 2.5 Pro Preview 06-05","lab":"google","date":"2025-06-05","description":"Advanced Gemini model for complex reasoning, coding, and multimodal analysis","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["application/pdf","image/png","image/jpeg","image/webp","image/heic","image/heif","text","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-pro-preview.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-r1-0528-qwen3-8b","name":"DeepSeek R1 0528 Qwen3 8B","lab":"deepseek","date":"2025-05-29","description":"DeepSeek R1 0528 distilled into Qwen3 8B for mathematics, coding, and reasoning","context":131072,"output":32000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1-0528-qwen3-8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-r1-0528","name":"DeepSeek R1 0528","lab":"deepseek","date":"2025-05-28","description":"May 2025 DeepSeek R1 update with improved mathematics, coding, and reasoning","context":163840,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1-0528.toml","kind":"model","articles":[{"title":"DeepSeek-R1-0528 Release","url":"https://api-docs.deepseek.com/news/news250528","date":"2025-05-28","published_at":"2025-05-28T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/codestral-embed-2505","name":"Codestral Embed","lab":"mistral","date":"2025-05-28","description":"Embedding model for code search, retrieval, and code-aware RAG pipelines","context":8192,"output":3072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/codestral-embed-2505.toml","kind":"model","articles":[{"title":"Codestral Embed","url":"https://mistral.ai/news/codestral-embed/","date":"2025-05-28","published_at":"2025-05-28T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-sonnet-4-0","name":"Claude Sonnet 4","lab":"anthropic","date":"2025-05-22","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","context":200000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-0.toml","kind":"model","articles":[{"title":"Released Claude Opus 4 and Claude Sonnet 4","url":"https://platform.claude.com/docs/en/release-notes/overview#may-22-2025","date":"2025-05-22","published_at":"2025-05-22T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"anthropic/claude-opus-4-0","name":"Claude Opus 4","lab":"anthropic","date":"2025-05-22","description":"Flagship Claude model for deep reasoning, coding, and long-horizon agents","context":200000,"output":32000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-0.toml","kind":"model","articles":[{"title":"Released Claude Opus 4 and Claude Sonnet 4","url":"https://platform.claude.com/docs/en/release-notes/overview#may-22-2025","date":"2025-05-22","published_at":"2025-05-22T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/devstral","name":"Devstral","lab":"mistral","date":"2025-05-21","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/devstral/","kind":"model","articles":[{"title":"Devstral","url":"https://mistral.ai/news/devstral/","date":"2025-05-21","published_at":"2025-05-21T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]},{"title":"Upgrading agentic coding capabilities with the new Devstral models","url":"https://mistral.ai/news/devstral-2507/","date":"2025-07-10","published_at":"2025-07-10T16:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/lyria-realtime-exp","name":"Lyria RealTime","lab":"google","date":"2025-05-20","description":"Experimental streaming music generation model steered in real time by weighted text prompts","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-realtime-exp.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-embedding-001","name":"Gemini Embedding 001","lab":"google","date":"2025-05-20","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","context":2048,"output":1,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-embedding-001.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.5-flash-preview-05-20","name":"Gemini 2.5 Flash Preview 05-20","lab":"google","date":"2025-05-20","description":"Preview snapshot of Gemini 2.5 Flash with controllable thinking budgets","context":1048576,"output":65536,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-preview-05-20.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-medium-2505","name":"Mistral Medium 3","lab":"mistral","date":"2025-05-07","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":131072,"output":131072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-2505.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-8b","name":"Qwen3 8B","lab":"alibaba","date":"2025-04-29","description":"Dense 8B Qwen3 model with switchable thinking for chat, reasoning, and tool use","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-prompt-guard-2-86m","name":"Llama Prompt Guard 2 86M","lab":"meta","date":"2025-04-29","description":"86M-parameter (mDeBERTa-base) multilingual classifier that detects prompt injection and jailbreak attempts","context":512,"output":512,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-prompt-guard-2-86m.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-prompt-guard-2-22m","name":"Llama Prompt Guard 2 22M","lab":"meta","date":"2025-04-29","description":"22M-parameter (DeBERTa-xsmall) English classifier that detects prompt injection and jailbreak attempts","context":512,"output":512,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-prompt-guard-2-22m.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-guard-4-12b","name":"Llama Guard 4 12B","lab":"meta","date":"2025-04-29","description":"Multimodal Llama 4-based safety classifier for moderating prompts and responses","context":163840,"output":163840,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-guard-4-12b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-32b","name":"Qwen3 32B","lab":"alibaba","date":"2025-04-28","description":"Dense open Qwen model for self-hosted chat, reasoning, and coding","context":131072,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-32b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-30b-a3b","name":"Qwen3 30B A3B","lab":"alibaba","date":"2025-04-28","description":"Sparse MoE Qwen model with 3B active parameters for efficient chat and reasoning","context":131072,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-30b-a3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen3-235b-a22b","name":"Qwen3 235B-A22B","lab":"alibaba","date":"2025-04-28","description":"Large open Qwen MoE for multilingual reasoning, coding, and tool use","context":131072,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-235b-a22b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-image-1","name":"GPT-Image-1","lab":"openai","date":"2025-04-24","description":"OpenAI image model for production generation, edits, and brand-safe visual workflows","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/webp"],"output_modalities":["image/png","image/jpeg","image/webp"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/o4-mini","name":"o4-mini","lab":"openai","date":"2025-04-16","description":"Fast o-series model for compact reasoning, coding, and tool use","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o4-mini.toml","kind":"model","articles":[{"title":"Introducing OpenAI o3 and o4-mini","url":"https://openai.com/index/introducing-o3-and-o4-mini","date":"2025-04-16","published_at":"2025-04-16T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/o3","name":"o3","lab":"openai","date":"2025-04-16","description":"Deliberate o-series reasoner for hard math, coding, and multi-step analysis","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3.toml","kind":"model","articles":[{"title":"Introducing OpenAI o3 and o4-mini","url":"https://openai.com/index/introducing-o3-and-o4-mini","date":"2025-04-16","published_at":"2025-04-16T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","lab":"nvidia","date":"2025-04-15","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.1-nemotron-70b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4.1-nano","name":"GPT-4.1 nano","lab":"openai","date":"2025-04-14","description":"Tiny GPT-4.1 option for classification, routing, and very high-volume tasks","context":1047576,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1-nano.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4.1-mini","name":"GPT-4.1 mini","lab":"openai","date":"2025-04-14","description":"Affordable GPT-4.1 lane for fast coding help and structured extraction","context":1047576,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4.1","name":"GPT-4.1","lab":"openai","date":"2025-04-14","description":"Long-lived GPT workhorse for coding, instruction following, and production apps","context":1047576,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1.toml","kind":"model","articles":[{"title":"Introducing GPT-4.1 in the API","url":"https://openai.com/index/gpt-4-1","date":"2025-04-14","published_at":"2025-04-14T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/pixtral-large-2502","name":"Pixtral Large (25.02)","lab":"mistral","date":"2025-04-08","description":"Mistral vision-language model for image understanding and multimodal chat","context":128000,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/pixtral-large-2502.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-3.1-nemotron-ultra-253b","name":"Llama 3.1 Nemotron Ultra 253B","lab":"nvidia","date":"2025-04-07","description":"Flagship Nemotron model for high-throughput reasoning and complex agents","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.1-nemotron-ultra-253b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-4-scout-17b-instruct","name":"Llama 4 Scout 17B Instruct","lab":"meta","date":"2025-04-05","description":"Open Llama with long-context vision for efficient multimodal agents","context":10000000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-4-scout-17b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-4-maverick-17b-instruct","name":"Llama 4 Maverick 17B Instruct","lab":"meta","date":"2025-04-05","description":"Open multimodal Llama for strong reasoning with efficient everyday serving","context":1000000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-4-maverick-17b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-chat-v3-0324","name":"DeepSeek V3 0324","lab":"deepseek","date":"2025-03-24","description":"DeepSeek chat model for instruction following, coding, and analysis","context":163840,"output":147456,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-chat-v3-0324.toml","kind":"model","articles":[{"title":"DeepSeek-V3-0324 Release","url":"https://api-docs.deepseek.com/news/news250325","date":"2025-03-25","published_at":"2025-03-25T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-4o-transcribe","name":"GPT-4o Transcribe","lab":"openai","date":"2025-03-20","description":"Speech-to-text model powered by GPT-4o for accurate transcription","context":16000,"output":2000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm","audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-transcribe.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4o-mini-transcribe","name":"GPT-4o Mini Transcribe","lab":"openai","date":"2025-03-20","description":"Speech-to-text model powered by GPT-4o Mini for fast, accurate transcription","context":16000,"output":2000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm","audio/pcm","audio/pcmu","audio/pcma"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-mini-transcribe.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4o-mini-tts","name":"GPT-4o Mini TTS","lab":"openai","date":"2025-03-20","description":"Text-to-speech model powered by GPT-4o Mini with steerable voice delivery","context":2000,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/mpeg","audio/opus","audio/aac","audio/flac","audio/wav","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-mini-tts.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/o1-pro","name":"o1-pro","lab":"openai","date":"2025-03-19","description":"O-series reasoning model for hard analysis, math, coding, and planning","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o1-pro.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","lab":"nvidia","date":"2025-03-18","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.3-nemotron-super-49b-v1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-small-3-1-24b-instruct-2503","name":"Mistral Small 3.1 24B","lab":"mistral","date":"2025-03-17","description":"Efficient multimodal model for instruction following, coding, reasoning, and function calling","context":128000,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-3-1-24b-instruct-2503.toml","kind":"model","articles":[{"title":"Mistral Small 3.1","url":"https://mistral.ai/news/mistral-small-3-1/","date":"2025-03-17","published_at":"2025-03-17T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Mistral Small 3.1"]},{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","lab":"google","date":"2025-03-12","description":"Open multimodal Gemma instruction model for efficient text generation and image understanding","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-4b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-3-27b-it","name":"Gemma 3 27B IT","lab":"google","date":"2025-03-12","description":"Largest open Gemma 3 instruction model for multilingual text generation and visual understanding","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-27b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","lab":"google","date":"2025-03-12","description":"Open multimodal Gemma instruction model for multilingual text generation and image understanding","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-12b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-ocr","name":"Mistral OCR","lab":"mistral","date":"2025-03-06","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/mistral-ocr/","kind":"model","articles":[{"title":"Mistral OCR","url":"https://mistral.ai/news/mistral-ocr/","date":"2025-03-06","published_at":"2025-03-06T17:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwq-plus","name":"QwQ Plus","lab":"alibaba","date":"2025-03-05","description":"Qwen reasoning model for deliberate problem solving, math, and coding","context":131072,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwq-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwq-32b","name":"QwQ 32B","lab":"alibaba","date":"2025-03-05","description":"Open reasoning model from the Qwen team for math, coding, and step-by-step problem solving","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwq-32b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-3-7-sonnet-20250219","name":"Claude Sonnet 3.7","lab":"anthropic","date":"2025-02-19","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","context":200000,"output":64000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-7-sonnet-20250219.toml","kind":"model","articles":[{"title":"Released Claude Sonnet 3.7","url":"https://platform.claude.com/docs/en/release-notes/overview#february-24th-2025","date":"2025-02-24","published_at":"2025-02-24T00:00:00+00:00","primary":true,"publisher":"anthropic","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/mistral-saba","name":"Saba","lab":"mistral","date":"2025-02-17","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":32768,"output":26214,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-saba.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-small-24b-instruct-2501","name":"Mistral Small 3","lab":"mistral","date":"2025-01-30","description":"Efficient Mistral model for fast chat, extraction, and production assistants","context":32768,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-24b-instruct-2501.toml","kind":"model","articles":[{"title":"Mistral Small 3","url":"https://mistral.ai/news/mistral-small-3/","date":"2025-01-30","published_at":"2025-01-30T12:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen2-5-vl-72b-instruct","name":"Qwen2.5-VL 72B Instruct","lab":"alibaba","date":"2025-01-26","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2-5-vl-72b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-r1-distill-qwen-32b","name":"DeepSeek-R1-Distill-Qwen-32B","lab":"deepseek","date":"2025-01-20","description":"R1 reasoning distilled into Qwen 2.5 32B for efficient open-weight step-by-step problem solving","context":131072,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1-distill-qwen-32b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-r1","name":"DeepSeek-R1","lab":"deepseek","date":"2025-01-20","description":"Classic open reasoning model for transparent math, coding, and deliberate problem solving","context":128000,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1.toml","kind":"model","articles":[{"title":"DeepSeek-R1 Release","url":"https://api-docs.deepseek.com/news/news250120","date":"2025-01-20","published_at":"2025-01-20T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/qwen-omni-turbo","name":"Qwen-Omni Turbo","lab":"alibaba","date":"2025-01-19","description":"Qwen omni model for text, vision, audio, and multimodal agent tasks","context":32768,"output":2048,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic","audio/amr","audio/wav","audio/3gpp","audio/aac","audio/mpeg","video/mp4","video/x-msvideo","video/x-matroska","video/quicktime","video/x-flv","video/x-ms-wmv"],"output_modalities":["text","audio/wav"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-omni-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/codestral-25.01","name":"Codestral 25.01","lab":"mistral","date":"2025-01-13","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/codestral-2501/","kind":"model","articles":[{"title":"Codestral 25.01","url":"https://mistral.ai/news/codestral-2501/","date":"2025-01-13","published_at":"2025-01-13T08:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"deepseek/deepseek-v3","name":"DeepSeek-V3","lab":"deepseek","date":"2024-12-26","description":"Open DeepSeek MoE chat model for coding, math, and general reasoning","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.toml","kind":"model","articles":[{"title":"🚀 Introducing DeepSeek-V3","url":"https://api-docs.deepseek.com/news/news1226","date":"2024-12-26","published_at":"2024-12-26T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/o3-mini","name":"o3-mini","lab":"openai","date":"2024-12-20","description":"Smaller o-series reasoner for economical coding, math, and planning tasks","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-mini.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.0-flash-lite","name":"Gemini 2.0 Flash-Lite","lab":"google","date":"2024-12-11","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","context":1048576,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.0-flash-lite.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"google/gemini-2.0-flash","name":"Gemini 2.0 Flash","lab":"google","date":"2024-12-11","description":"Earlier Gemini Flash workhorse for responsive multimodal apps and tool use","context":1048576,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/heic","image/heif","audio/wav","audio/mp3","audio/aiff","audio/aac","audio/ogg","audio/flac","audio/mpeg","audio/m4a","audio/l16","audio/opus","audio/alaw","audio/mulaw","audio/webm","video/mp4","video/mpeg","video/mov","video/avi","video/x-flv","video/mpg","video/webm","video/wmv","video/3gpp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.0-flash.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.3-70b-instruct","name":"Llama-3.3-70B-Instruct","lab":"meta","date":"2024-12-06","description":"Popular open Llama workhorse for multilingual chat, coding, and self-hosting","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.3-70b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4o-2024-11-20","name":"GPT-4o","lab":"openai","date":"2024-11-20","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-2024-11-20.toml","kind":"model","articles":[{"title":"Introducing GPT-4o and more tools to ChatGPT free users","url":"https://openai.com/index/gpt-4o-and-more-tools-to-chatgpt-free","date":"2024-05-13","published_at":"2024-05-13T10:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-large-2411","name":"Mistral Large 2.1","lab":"mistral","date":"2024-11-18","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","context":131072,"output":16384,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-2411.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen2.5-coder-32b-instruct","name":"Qwen2.5-Coder-32B-Instruct","lab":"alibaba","date":"2024-11-12","description":"Open coding-focused Qwen model for code generation, repair, and repository reasoning","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2.5-coder-32b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen2.5-coder-0.5b","name":"Qwen2.5-Coder-0.5B","lab":"alibaba","date":"2024-11-12","description":"Tiny open Qwen code model for lightweight completion and on-device coding","context":32768,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2.5-coder-0.5b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-turbo","name":"Qwen Turbo","lab":"alibaba","date":"2024-11-01","description":"Efficient Qwen model for fast chat, extraction, and high-volume workloads","context":1000000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-3-5-sonnet-20241022","name":"Claude Sonnet 3.5 v2","lab":"anthropic","date":"2024-10-22","description":"Balanced Claude model for coding, analysis, agent workflows, and cost control","context":200000,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-5-sonnet-20241022.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"anthropic/claude-3-5-haiku-20241022","name":"Claude Haiku 3.5","lab":"anthropic","date":"2024-10-22","description":"Fast Claude model for responsive assistance, classification, and lightweight agents","context":200000,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-5-haiku-20241022.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-8b-instruct-2410","name":"Ministral 8B Instruct","lab":"mistral","date":"2024-10-16","description":"Efficient open Mistral edge model for on-device chat and function calling","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-8b-instruct-2410.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/ministral-3b","name":"Ministral 3B","lab":"mistral","date":"2024-10-16","description":"Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/whisper-large-v3-turbo","name":"Whisper Large v3 Turbo","lab":"openai","date":"2024-10-01","description":"Speech transcription model for accurate audio-to-text and captioning workflows","context":448,"output":448,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/whisper-large-v3-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","lab":"meta","date":"2024-09-25","description":"Large open multimodal Llama model for image reasoning, document QA, and captioning","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-90b-vision-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-3b","name":"Llama-3.2-3B","lab":"meta","date":"2024-09-25","description":"Small open Llama base model for lightweight text generation and self-hosting","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-3b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-1b","name":"Llama-3.2-1B","lab":"meta","date":"2024-09-25","description":"Compact open Llama base model for lightweight and on-device use","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-1b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama-3.2-11B-Vision-Instruct","lab":"meta","date":"2024-09-25","description":"Open multimodal Llama model for image understanding, captioning, and visual QA","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-11b-vision-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-3b-instruct","name":"Llama 3.2 3B Instruct","lab":"meta","date":"2024-09-25","description":"Small instruction-tuned Llama model for multilingual dialogue and agentic retrieval","context":131072,"output":131072,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-3b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.2-1b-instruct","name":"Llama 3.2 1B Instruct","lab":"meta","date":"2024-09-25","description":"Compact instruction-tuned Llama model for multilingual dialogue and on-device assistants","context":131072,"output":32000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-1b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen2.5-7b-instruct","name":"Qwen2.5 7B Instruct","lab":"alibaba","date":"2024-09-19","description":"Small open Qwen2.5 instruction model for chat, structured output, and tool use","context":131072,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2.5-7b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/o1","name":"o1","lab":"openai","date":"2024-09-12","description":"O-series reasoning model for hard analysis, math, coding, and planning","context":200000,"output":100000,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o1.toml","kind":"model","articles":[{"title":"Introducing OpenAI o1","url":"https://openai.com/index/introducing-openai-o1-preview","date":"2024-09-12","published_at":"2024-09-12T10:03:00+00:00","primary":true,"publisher":"openai","also":[]},{"title":"OpenAI o1 and new tools for developers","url":"https://openai.com/index/o1-and-new-tools-for-developers","date":"2024-12-17","published_at":"2024-12-17T00:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"mistral/pixtral-12b","name":"Pixtral 12B","lab":"mistral","date":"2024-09-11","description":"Mistral vision-language model for image understanding and multimodal chat","context":128000,"output":128000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","image/png","image/jpeg","image/webp","image/gif"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/pixtral-12b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"deepseek/deepseek-v2.5","name":"DeepSeek-V2.5","lab":"deepseek","date":"2024-09-05","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://api-docs.deepseek.com/news/news0905","kind":"model","articles":[{"title":"DeepSeek-V2.5: A New Open-Source Model Combining General and Coding Capabilities","url":"https://api-docs.deepseek.com/news/news0905","date":"2024-09-05","published_at":"2024-09-05T00:00:00+00:00","primary":true,"publisher":"deepseek","also":[]}],"confirmed":true,"date_source":"official"},{"id":"nvidia/nemotron-mini-4b-instruct","name":"Nemotron Mini 4B Instruct","lab":"nvidia","date":"2024-08-21","description":"Compact Nemotron model for efficient reasoning and deployable AI agents","context":128000,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-mini-4b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-2-beta","name":"Grok-2 Beta","lab":"xai","date":"2024-08-13","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-2","kind":"model","articles":[{"title":"Grok-2 Beta Release","url":"https://x.ai/news/grok-2","date":"2024-08-13","published_at":"2024-08-13T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"openai/gpt-4o-2024-08-06","name":"GPT-4o","lab":"openai","date":"2024-08-06","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-2024-08-06.toml","kind":"model","articles":[{"title":"Introducing GPT-4o and more tools to ChatGPT free users","url":"https://openai.com/index/gpt-4o-and-more-tools-to-chatgpt-free","date":"2024-05-13","published_at":"2024-05-13T10:00:00+00:00","primary":false,"publisher":"openai","also":[]}],"confirmed":false,"date_source":"catalog"},{"id":"google/gemma-2-2b-it","name":"Gemma 2 2B IT","lab":"google","date":"2024-07-31","description":"Small open Gemma 2 instruction model for lightweight chat and on-device use","context":8192,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-2-2b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-large-2407","name":"Mistral Large 2407","lab":"mistral","date":"2024-07-24","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","context":131072,"output":104857,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-2407.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-guard-3-8b","name":"Llama-Guard-3-8B","lab":"meta","date":"2024-07-23","description":"Llama 3.1-based safety classifier for moderating prompts and model responses","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-guard-3-8b.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.1-8b-instruct","name":"Llama-3.1-8B-Instruct","lab":"meta","date":"2024-07-23","description":"Compact open Llama model for lightweight chat, drafting, and self-hosting","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.1-8b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"meta/llama-3.1-70b-instruct","name":"Llama-3.1-70B-Instruct","lab":"meta","date":"2024-07-23","description":"Open Llama instruction model for multilingual chat, reasoning, and coding","context":128000,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.1-70b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-nemo","name":"Mistral Nemo","lab":"mistral","date":"2024-07-18","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","context":128000,"output":128000,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-nemo.toml","kind":"model","articles":[{"title":"Mistral NeMo","url":"https://mistral.ai/news/mistral-nemo/","date":"2024-07-18","published_at":"2024-07-18T08:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"openai/gpt-4o-mini","name":"GPT-4o mini","lab":"openai","date":"2024-07-18","description":"Small omni GPT for cheap multimodal assistance and production-scale traffic","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-mini.toml","kind":"model","articles":[{"title":"GPT-4o mini: advancing cost-efficient intelligence","url":"https://openai.com/index/gpt-4o-mini-advancing-cost-efficient-intelligence","date":"2024-07-18","published_at":"2024-07-18T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"mistral/codestral-mamba","name":"Codestral Mamba","lab":"mistral","date":"2024-07-16","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://mistral.ai/news/codestral-mamba/","kind":"model","articles":[{"title":"Codestral Mamba","url":"https://mistral.ai/news/codestral-mamba/","date":"2024-07-16","published_at":"2024-07-16T08:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"official"},{"id":"google/gemma-2-27b-it","name":"Gemma 2 27B","lab":"google","date":"2024-07-13","description":"Open Gemma instruction model for efficient chat and self-hosted deployments","context":8192,"output":2048,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-2-27b-it.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/codestral-22b-v0.1","name":"Codestral-22B-v0.1","lab":"mistral","date":"2024-05-29","description":"Open Mistral code model for fill-in-the-middle and 80+ programming languages","context":32768,"output":8192,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/codestral-22b-v0.1.toml","kind":"model","articles":[{"title":"Codestral","url":"https://mistral.ai/news/codestral/","date":"2024-05-29","published_at":"2024-05-29T09:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Codestral"]},{"id":"mistral/mistral-7b-instruct-v0.3","name":"Mistral 7B Instruct v0.3","lab":"mistral","date":"2024-05-22","description":"Open 7B Mistral instruction model with function calling","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-7b-instruct-v0.3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4o","name":"GPT-4o","lab":"openai","date":"2024-05-13","description":"Omni-era GPT for multimodal chat, practical coding, and general assistants","context":128000,"output":16384,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o.toml","kind":"model","articles":[{"title":"Introducing GPT-4o and more tools to ChatGPT free users","url":"https://openai.com/index/gpt-4o-and-more-tools-to-chatgpt-free","date":"2024-05-13","published_at":"2024-05-13T10:00:00+00:00","primary":true,"publisher":"openai","also":[]}],"confirmed":true,"date_source":"catalog"},{"id":"alibaba/gte-large-en-v1.5","name":"GTE Large EN v1.5","lab":"alibaba","date":"2024-04-20","description":"English long-context text embedding model producing 1024-dimensional vectors","context":8192,"output":0,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/gte-large-en-v1.5.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mixtral-8x22b-instruct","name":"Mixtral 8x22B Instruct","lab":"mistral","date":"2024-04-17","description":"Mistral model for multilingual chat, reasoning, and tool-assisted workflows","context":65536,"output":52428,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mixtral-8x22b-instruct.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-1.5-vision-preview","name":"Grok-1.5 Vision Preview","lab":"xai","date":"2024-04-12","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-1.5v","kind":"model","articles":[{"title":"Grok-1.5 Vision Preview","url":"https://x.ai/news/grok-1.5v","date":"2024-04-12","published_at":"2024-04-12T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"alibaba/qwen-vl-max","name":"Qwen-VL Max","lab":"alibaba","date":"2024-04-08","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":131072,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-vl-max.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-max","name":"Qwen Max","lab":"alibaba","date":"2024-04-03","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","context":32768,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-max.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"xai/grok-1.5","name":"Grok-1.5","lab":"xai","date":"2024-03-28","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-1.5","kind":"model","articles":[{"title":"Announcing Grok-1.5","url":"https://x.ai/news/grok-1.5","date":"2024-03-28","published_at":"2024-03-28T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"xai/grok-1","name":"Grok-1","lab":"xai","date":"2024-03-17","description":"","context":null,"output":null,"open_weights":null,"reasoning":null,"tools":null,"input_modalities":[],"output_modalities":[],"source":"https://x.ai/news/grok-os","kind":"model","articles":[{"title":"Open Release of Grok-1","url":"https://x.ai/news/grok-os","date":"2024-03-17","published_at":"2024-03-17T00:00:00+00:00","primary":true,"publisher":"xai","also":[]}],"confirmed":true,"date_source":"official"},{"id":"anthropic/claude-3-haiku-20240307","name":"Claude Haiku 3","lab":"anthropic","date":"2024-03-13","description":"Legacy model retained for compatibility with older integrations","context":200000,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-haiku-20240307.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mistral-large","name":"Mistral Large","lab":"mistral","date":"2024-02-26","description":"Flagship Mistral model for advanced reasoning, coding, and multilingual work","context":128000,"output":102400,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","application/pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/text-embedding-3-small","name":"text-embedding-3-small","lab":"openai","date":"2024-01-25","description":"Small, efficient OpenAI text embedding model","context":8192,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/text-embedding-3-small.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/text-embedding-3-large","name":"text-embedding-3-large","lab":"openai","date":"2024-01-25","description":"Most capable OpenAI embedding model for English and non-English text","context":8192,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/text-embedding-3-large.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-vl-plus","name":"Qwen-VL Plus","lab":"alibaba","date":"2024-01-25","description":"Qwen vision-language model for visual reasoning, documents, and agent tasks","context":131072,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/bmp","image/jpeg","image/png","image/tiff","image/webp","image/heic"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-vl-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"alibaba/qwen-plus","name":"Qwen Plus","lab":"alibaba","date":"2024-01-25","description":"Qwen instruction model for multilingual chat, reasoning, and tool use","context":1000000,"output":32768,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-plus.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"mistral/mixtral-8x7b-instruct-v0.1","name":"Mixtral 8x7B Instruct v0.1","lab":"mistral","date":"2023-12-11","description":"Open sparse mixture-of-experts Mistral instruction model","context":32768,"output":32768,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mixtral-8x7b-instruct-v0.1.toml","kind":"model","articles":[{"title":"Mixtral of experts","url":"https://mistral.ai/news/mixtral-of-experts/","date":"2023-12-11","published_at":"2023-12-11T07:00:00+00:00","primary":true,"publisher":"mistral","also":[]}],"confirmed":true,"date_source":"catalog","release_aliases":["Mixtral"]},{"id":"mistral/mistral-embed","name":"Mistral Embed","lab":"mistral","date":"2023-12-11","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","context":8000,"output":3072,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-embed.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/whisper-large-v3","name":"Whisper 3 Large","lab":"openai","date":"2023-11-06","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","context":448,"output":4096,"open_weights":true,"reasoning":null,"tools":null,"input_modalities":["audio/flac","audio/mpeg","audio/mp4","audio/ogg","audio/wav","audio/webm"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/whisper-large-v3.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/tts-1-hd","name":"TTS-1 HD","lab":"openai","date":"2023-11-06","description":"Text-to-speech model optimized for audio quality","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/mpeg","audio/opus","audio/aac","audio/flac","audio/wav","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/tts-1-hd.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/tts-1","name":"TTS-1","lab":"openai","date":"2023-11-06","description":"Text-to-speech model optimized for low latency","context":null,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["audio/mpeg","audio/opus","audio/aac","audio/flac","audio/wav","audio/pcm"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/tts-1.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4-turbo","name":"GPT-4 Turbo","lab":"openai","date":"2023-11-06","description":"Compact GPT model for low-latency assistance and high-volume workloads","context":128000,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text","image/jpeg","image/png","image/gif","image/webp"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-4","name":"GPT-4","lab":"openai","date":"2023-11-06","description":"GPT model for general reasoning, writing, coding, and tool-assisted tasks","context":8192,"output":8192,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.toml","kind":"model","articles":[{"title":"GPT-4","url":"https://openai.com/index/gpt-4","date":"2023-03-14","published_at":"2023-03-14T00:00:00+00:00","primary":false,"publisher":"openai","also":["https://openai.com/index/gpt-4-research"]}],"confirmed":false,"date_source":"catalog"},{"id":"openai/gpt-3.5-turbo","name":"GPT-3.5-turbo","lab":"openai","date":"2023-03-01","description":"Compact GPT model for low-latency assistance and high-volume workloads","context":16385,"output":4096,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-3.5-turbo.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"},{"id":"openai/text-embedding-ada-002","name":"text-embedding-ada-002","lab":"openai","date":"2022-12-15","description":"Legacy OpenAI text embedding model","context":8192,"output":0,"open_weights":false,"reasoning":null,"tools":null,"input_modalities":["text"],"output_modalities":["embedding"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/text-embedding-ada-002.toml","kind":"model","articles":[],"confirmed":false,"date_source":"catalog"}],"model_aliases":{"meta/muse-wonder":{"name":"Muse Wonder","models":["meta/muse-wonder-1.0"]},"anthropic/claude-haiku-5.5":{"name":"Claude Haiku 5.5","models":["anthropic/claude-haiku-5-5"]},"google/nano-banana-2.1":{"name":"Nano Banana 2.1","models":["google/gemini-nano-banana-2.1"]},"xai/imagine-video-1.5-lite":{"name":"Imagine Video 1.5 Lite","models":["xai/grok-imagine-video-1.5-lite"]},"anthropic/claude-sonnet-5.5":{"name":"Claude Sonnet 5.5","models":["anthropic/claude-sonnet-5-5"]},"alibaba/qwen-3.8-max-prime":{"name":"Qwen 3.8 Max Prime","models":["alibaba/qwen3.8-max-prime"]},"anthropic/claude-opus-5.5":{"name":"Claude Opus 5.5","models":["anthropic/claude-opus-5-5"]},"anthropic/claude-mythos-5.1":{"name":"Claude Mythos 5.1","models":["anthropic/claude-mythos-5-1"]},"anthropic/claude-fable-5.1":{"name":"Claude Fable 5.1","models":["anthropic/claude-fable-5-1"]},"nvidia/nemotron-3.5-lightning-30b-a3b":{"name":"Nemotron 3.5 Lightning 30B A3B","models":["nvidia/nemotron-3.5-lightning"]},"xai/imagine-image-2.0":{"name":"Imagine Image 2.0","models":["xai/grok-imagine-image-2.0"]},"alibaba/wan3.0":{"name":"Wan3.0","models":["alibaba/wan3.0-video"]},"mistral/mistral-ocr-4.1":{"name":"Mistral OCR 4.1","models":["mistral/mistral-ocr-4-1"]},"openai/gpt-5.6":{"name":"GPT-5.6","models":["openai/gpt-5.6-terra","openai/gpt-5.6-sol","openai/gpt-5.6-luna"]},"meta/muse-image":{"name":"Muse Image","models":["meta/muse-image-1.0"]},"google/nano-banana-2-lite":{"name":"Nano Banana 2 Lite","models":["google/gemini-3.1-flash-lite-image"]},"google/gemma-4-12b":{"name":"Gemma 4 12B","models":["google/gemma-4-12b-it"]},"xai/imagine-video-1.5":{"name":"Imagine Video 1.5","models":["xai/grok-imagine-video-1.5"]},"google/nano-banana-pro":{"name":"Nano Banana Pro","models":["google/gemini-3-pro-image"]},"google/nano-banana-2":{"name":"Nano Banana 2","models":["google/gemini-3.1-flash-image"]},"anthropic/claude-opus-4.8":{"name":"Claude Opus 4.8","models":["anthropic/claude-opus-4-8"]},"mistral/mistral-medium-3.5":{"name":"Mistral Medium 3.5","models":["mistral/mistral-medium-3-5","mistral/mistral-medium-2604"]},"google/gemini-deep-research-preview":{"name":"Gemini Deep Research Preview","models":["google/deep-research-preview-04-2026"]},"google/deep-research-max-preview":{"name":"Deep Research Max Preview","models":["google/deep-research-max-preview-04-2026"]},"anthropic/claude-opus-4.7":{"name":"Claude Opus 4.7","models":["anthropic/claude-opus-4-7"]},"google/gemini-3.1-flash-tts":{"name":"Gemini 3.1 Flash TTS","models":["google/gemini-3.1-flash-tts-preview"]},"meta/muse-spark":{"name":"Muse Spark","models":["meta/muse-spark-1.1"]},"xai/imagine-image-quality":{"name":"Imagine Image Quality","models":["xai/grok-imagine-image-quality"]},"google/gemma-4-e4b-it":{"name":"Gemma 4 E4B IT","models":["google/gemma-4-E4B-it"]},"google/gemma-4":{"name":"Gemma 4","models":["google/gemma-4-E4B-it","google/gemma-4-E2B-it","google/gemma-4-31b-it","google/gemma-4-26b-a4b-it"]},"google/gemma-4-e2b-it":{"name":"Gemma 4 E2B IT","models":["google/gemma-4-E2B-it"]},"google/veo-3.1-lite-preview":{"name":"Veo 3.1 Lite Preview","models":["google/veo-3.1-lite-generate-preview"]},"google/gemini-3.1-flash-live":{"name":"Gemini 3.1 Flash Live","models":["google/gemini-3.1-flash-live-preview"]},"google/lyria-3-pro":{"name":"Lyria 3 Pro","models":["google/lyria-3-pro-preview"]},"mistral/voxtral-mini-tts":{"name":"Voxtral Mini TTS","models":["mistral/voxtral-mini-tts-2603"]},"mistral/mistral-small-4":{"name":"Mistral Small 4","models":["mistral/mistral-small-2603"]},"xai/grok-4.20-reasoning":{"name":"Grok 4.20 (Reasoning)","models":["xai/grok-4.20-0309-reasoning"]},"xai/grok-4.20-non-reasoning":{"name":"Grok 4.20 (Non-Reasoning)","models":["xai/grok-4.20-0309-non-reasoning"]},"mistral/mistral-moderation-26.03":{"name":"Mistral Moderation 26.03","models":["mistral/mistral-moderation-2603"]},"google/nano-banana-2-preview":{"name":"Nano Banana 2 Preview","models":["google/gemini-3.1-flash-image-preview"]},"google/gemini-3.1-pro-preview-custom-tools":{"name":"Gemini 3.1 Pro Preview Custom Tools","models":["google/gemini-3.1-pro-preview-customtools"]},"google/gemini-3.1-pro":{"name":"Gemini 3.1 Pro","models":["google/gemini-3.1-pro-preview-customtools","google/gemini-3.1-pro-preview"]},"anthropic/claude-sonnet-4.6":{"name":"Claude Sonnet 4.6","models":["anthropic/claude-sonnet-4-6"]},"alibaba/qwen3.5":{"name":"Qwen3.5","models":["alibaba/qwen3.5-397b-a17b"]},"anthropic/claude-opus-4.6":{"name":"Claude Opus 4.6","models":["anthropic/claude-opus-4-6"]},"mistral/voxtral-mini-transcribe-realtime":{"name":"Voxtral Mini Transcribe Realtime","models":["mistral/voxtral-mini-transcribe-realtime-2602"]},"mistral/voxtral-mini-transcribe-2":{"name":"Voxtral Mini Transcribe 2","models":["mistral/voxtral-mini-2602"]},"xai/imagine-video":{"name":"Imagine Video","models":["xai/grok-imagine-video"]},"xai/imagine-image":{"name":"Imagine Image","models":["xai/grok-imagine-image"]},"xai/x-ai-grok-4-fast-reasoning":{"name":"X-Ai/Grok-4-Fast-Reasoning","models":["xai/grok-4-fast-reasoning"]},"xai/x-ai-grok-4-fast-non-reasoning":{"name":"X-Ai/Grok-4-Fast-Non-Reasoning","models":["xai/grok-4-fast-non-reasoning"]},"mistral/mistral-ocr-3":{"name":"Mistral OCR 3","models":["mistral/mistral-ocr-2512"]},"google/gemini-3-flash":{"name":"Gemini 3 Flash","models":["google/gemini-3-flash-preview"]},"mistral/devstral-2":{"name":"Devstral 2","models":["mistral/devstral-2512"]},"mistral/mistral-large-3":{"name":"Mistral Large 3","models":["mistral/mistral-large-2512"]},"mistral/ministral-3-8b-2512":{"name":"Ministral 3 8B 2512","models":["mistral/ministral-8b-2512"]},"mistral/ministral-3-8b":{"name":"Ministral 3 8B","models":["mistral/ministral-3-8b-instruct-2512"]},"mistral/ministral-3-3b-2512":{"name":"Ministral 3 3B 2512","models":["mistral/ministral-3b-2512"]},"mistral/ministral-3-3b":{"name":"Ministral 3 3B","models":["mistral/ministral-3-3b-instruct-2512"]},"mistral/ministral-3-14b-2512":{"name":"Ministral 3 14B 2512","models":["mistral/ministral-14b-2512"]},"mistral/ministral-3-14b":{"name":"Ministral 3 14B","models":["mistral/ministral-3-14b-instruct-2512"]},"anthropic/claude-opus-4.5":{"name":"Claude Opus 4.5","models":["anthropic/claude-opus-4-5"]},"google/nano-banana-pro-preview":{"name":"Nano Banana Pro Preview","models":["google/gemini-3-pro-image-preview"]},"google/gemini-3":{"name":"Gemini 3","models":["google/gemini-3-pro-preview"]},"google/veo-3.1-preview":{"name":"Veo 3.1 Preview","models":["google/veo-3.1-generate-preview"]},"google/veo-3.1-fast-preview":{"name":"Veo 3.1 Fast Preview","models":["google/veo-3.1-fast-generate-preview"]},"alibaba/qwen3-vl-flash-alibaba-cloud":{"name":"Qwen3 VL Flash (Alibaba Cloud)","models":["alibaba/qwen3-vl-flash"]},"anthropic/claude-haiku-4.5":{"name":"Claude Haiku 4.5","models":["anthropic/claude-haiku-4-5"]},"google/gemini-2.5-computer-use-preview":{"name":"Gemini 2.5 Computer Use Preview","models":["google/gemini-2.5-computer-use-preview-10-2025"]},"anthropic/claude-sonnet-4.5":{"name":"Claude Sonnet 4.5","models":["anthropic/claude-sonnet-4-5"]},"mistral/magistral-small-1.2":{"name":"Magistral Small 1.2","models":["mistral/magistral-small-2509"]},"moonshotai/kimi-k2-instruct-0905":{"name":"Kimi K2 Instruct 0905","models":["moonshotai/kimi-k2-0905"]},"xai/x-ai-grok-code-fast-1":{"name":"x-AI/Grok-Code-Fast 1","models":["xai/grok-code-fast-1"]},"google/nano-banana":{"name":"Nano Banana","models":["google/gemini-2.5-flash-image"]},"deepseek/deepseek-v3.1":{"name":"DeepSeek V3.1","models":["deepseek/deepseek-chat-v3.1"]},"anthropic/claude-opus-4.1":{"name":"Claude Opus 4.1","models":["anthropic/claude-opus-4-1"]},"mistral/codestral-25.08":{"name":"Codestral 25.08","models":["mistral/codestral-2508"]},"mistral/voxtral":{"name":"Voxtral","models":["mistral/voxtral-small-24b-2507","mistral/voxtral-mini-3b-2507"]},"moonshotai/kimi-k2-0711":{"name":"Kimi K2 0711","models":["moonshotai/kimi-k2"]},"mistral/devstral-small":{"name":"Devstral Small","models":["mistral/devstral-small-2507"]},"mistral/devstral-medium":{"name":"Devstral Medium","models":["mistral/devstral-medium-2507"]},"mistral/mistral-small-3.2-24b":{"name":"Mistral Small 3.2 24B","models":["mistral/mistral-small-3.2-24b-instruct"]},"mistral/mistral-small-3.2":{"name":"Mistral Small 3.2","models":["mistral/mistral-small-2506"]},"mistral/magistral-small":{"name":"Magistral Small","models":["mistral/magistral-small-2506"]},"mistral/magistral":{"name":"Magistral","models":["mistral/magistral-small-2506"]},"google/gemini-2.5-pro-preview-06-05":{"name":"Gemini 2.5 Pro Preview 06-05","models":["google/gemini-2.5-pro-preview"]},"mistral/codestral-embed":{"name":"Codestral Embed","models":["mistral/codestral-embed-2505"]},"anthropic/claude-sonnet-4":{"name":"Claude Sonnet 4","models":["anthropic/claude-sonnet-4-0"]},"anthropic/claude-opus-4":{"name":"Claude Opus 4","models":["anthropic/claude-opus-4-0"]},"google/lyria-realtime":{"name":"Lyria RealTime","models":["google/lyria-realtime-exp"]},"mistral/mistral-medium-3":{"name":"Mistral Medium 3","models":["mistral/mistral-medium-2505"]},"mistral/pixtral-large-25.02":{"name":"Pixtral Large (25.02)","models":["mistral/pixtral-large-2502"]},"deepseek/deepseek-v3-0324":{"name":"DeepSeek V3 0324","models":["deepseek/deepseek-chat-v3-0324"]},"mistral/mistral-small-3.1-24b":{"name":"Mistral Small 3.1 24B","models":["mistral/mistral-small-3-1-24b-instruct-2503"]},"mistral/mistral-small-3.1":{"name":"Mistral Small 3.1","models":["mistral/mistral-small-3-1-24b-instruct-2503"]},"anthropic/claude-sonnet-3.7":{"name":"Claude Sonnet 3.7","models":["anthropic/claude-3-7-sonnet-20250219"]},"mistral/saba":{"name":"Saba","models":["mistral/mistral-saba"]},"mistral/mistral-small-3":{"name":"Mistral Small 3","models":["mistral/mistral-small-24b-instruct-2501"]},"alibaba/qwen2.5-vl-72b-instruct":{"name":"Qwen2.5-VL 72B Instruct","models":["alibaba/qwen2-5-vl-72b-instruct"]},"openai/gpt-4o":{"name":"GPT-4o","models":["openai/gpt-4o-2024-11-20","openai/gpt-4o-2024-08-06"]},"mistral/mistral-large-2.1":{"name":"Mistral Large 2.1","models":["mistral/mistral-large-2411"]},"anthropic/claude-sonnet-3.5-v2":{"name":"Claude Sonnet 3.5 v2","models":["anthropic/claude-3-5-sonnet-20241022"]},"anthropic/claude-haiku-3.5":{"name":"Claude Haiku 3.5","models":["anthropic/claude-3-5-haiku-20241022"]},"mistral/ministral-8b-instruct":{"name":"Ministral 8B Instruct","models":["mistral/ministral-8b-instruct-2410"]},"google/gemma-2-27b":{"name":"Gemma 2 27B","models":["google/gemma-2-27b-it"]},"mistral/codestral":{"name":"Codestral","models":["mistral/codestral-22b-v0.1"]},"anthropic/claude-haiku-3":{"name":"Claude Haiku 3","models":["anthropic/claude-3-haiku-20240307"]},"mistral/mixtral":{"name":"Mixtral","models":["mistral/mixtral-8x7b-instruct-v0.1"]},"openai/whisper-3-large":{"name":"Whisper 3 Large","models":["openai/whisper-large-v3"]}},"release_count":485,"confirmed_count":179,"release_sources":[{"id":"openai-news","lab":"openai","url":"https://openai.com/news/rss.xml","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":1325,"releases_seen":44,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"anthropic-news","lab":"anthropic","url":"https://www.anthropic.com/news","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":26,"releases_seen":0,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"claude-blog","lab":"anthropic","url":"https://claude.dev/blog/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":10,"releases_seen":0,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"claude-release-notes","lab":"anthropic","url":"https://platform.claude.com/docs/en/release-notes/overview.md","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":13,"releases_seen":13,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"deepmind-blog","lab":"google","url":"https://deepmind.google/blog/rss.xml","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":100,"releases_seen":31,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"google-blog","lab":"google","url":"https://blog.google/products/gemini/rss/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":20,"releases_seen":9,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"meta-blog","lab":"meta","url":"https://ai.meta.com/blog/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":10,"releases_seen":3,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"xai-news","lab":"xai","url":"https://x.ai/news","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":89,"releases_seen":24,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"deepseek-news","lab":"deepseek","url":"https://api-docs.deepseek.com/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":19,"releases_seen":14,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"mistral-news","lab":"mistral","url":"https://mistral.ai/news/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":92,"releases_seen":28,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"qwen-research","lab":"alibaba","url":"https://qwen.ai/api/v2/article/retrieval?type=qwen_ai&language=en-US","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":40,"releases_seen":35,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"kimi-blog","lab":"moonshotai","url":"https://www.kimi.ai/blog/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":10,"releases_seen":6,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"zai-releases","lab":"zhipuai","url":"https://docs.z.ai/release-notes/new-released.md","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":8,"releases_seen":8,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"nvidia-blog","lab":"nvidia","url":"https://blogs.nvidia.com/blog/category/generative-ai/feed/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":18,"releases_seen":0,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"},{"id":"nvidia-developer","lab":"nvidia","url":"https://developer.nvidia.com/blog/feed/","last_attempt_at":"2026-10-27T04:15:12+00:00","error":null,"entries_seen":100,"releases_seen":0,"last_success_at":"2026-10-27T04:15:12+00:00","status":"ok"}],"releases_checked_at":"2026-10-27T04:15:12+00:00"}