{"updated_at":"2026-09-11T23:05:13+00:00","source":"Models.dev","source_url":"https://github.com/anomalyco/models.dev","source_digest":"49c653e06b3007897131b914154f52bda12344e1f1e2896a362be01a779ed09a","coverage_start":"2023-03-01","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":8,"future_date":0,"alias":23},"labs":[{"id":"openai","name":"OpenAI","mark":"O","color":"#f5f5f5"},{"id":"anthropic","name":"Anthropic","mark":"A","color":"#e8a886"},{"id":"google","name":"Google","mark":"G","color":"#8db9ff"},{"id":"meta","name":"Meta","mark":"M","color":"#899bff"},{"id":"xai","name":"xAI","mark":"x","color":"#c7c9d1"},{"id":"deepseek","name":"DeepSeek","mark":"D","color":"#72b9e9"},{"id":"mistral","name":"Mistral","mark":"▥","color":"#f0bc67"},{"id":"alibaba","name":"Qwen","mark":"Q","color":"#b6a0f0"},{"id":"moonshotai","name":"Moonshot AI","mark":"K","color":"#ddabd6"},{"id":"zhipuai","name":"Z.ai","mark":"Z","color":"#9dc9c3"},{"id":"nvidia","name":"NVIDIA","mark":"N","color":"#b2d77b"}],"models":[{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4.1-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-astra-fast.toml"},{"id":"openai/gpt-6-astra","name":"GPT-6 Astra","lab":"openai","date":"2026-09-04","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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-6-astra.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.3.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.8-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max-0902.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-fable-5-1.toml"},{"id":"alibaba/qwen3.8-flash-next","name":"Qwen3.8 Flash Next","lab":"alibaba","date":"2026-08-27","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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-flash-next.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.3-flash.toml"},{"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":false,"tools":false,"input_modalities":["audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-transcribe-live.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-flash.toml"},{"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":false,"reasoning":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-vision-exp.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.3.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-27b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.7-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.6.toml"},{"id":"deepseek/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","lab":"deepseek","date":"2026-08-12","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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro-0813.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-2.4t-a95b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-lightning.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-glimmer-30b.toml"},{"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":8000,"output":0,"open_weights":false,"reasoning":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-image-2.0.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.2.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-0731.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-5.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.6-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-flash-lite.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.8-max-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k3.toml"},{"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":65536,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-terra.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-sol.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.6-luna.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.5.toml"},{"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":true,"tools":true,"input_modalities":["text","audio","image"],"output_modalities":["text","audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-2.1.toml"},{"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":true,"tools":false,"input_modalities":["text","image","video"],"output_modalities":["video"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-omni-flash-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite-image.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-5.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.2.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.7-code-highspeed.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.7-code.toml"},{"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":false,"tools":false,"input_modalities":["audio"],"output_modalities":["audio","text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-live-translate-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-mythos-5.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-fable-5.toml"},{"id":"nvidia/nemotron-3.5-content-safety","name":"Nemotron 3.5 Content Safety","lab":"nvidia","date":"2026-06-04","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":8192,"open_weights":true,"reasoning":true,"tools":false,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3.5-content-safety.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-ultra-550b-a55b.toml"},{"id":"alibaba/qwen3.7-plus","name":"Qwen3.7 Plus","lab":"alibaba","date":"2026-06-02","description":"Multimodal Qwen workhorse for long-context agents, visual inputs, and coding","context":1000000,"output":64000,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-plus.toml"},{"id":"xai/grok-imagine-video-1.5","name":"Grok Imagine Video 1.5","lab":"xai","date":"2026-05-30","description":"Video model for image-to-video generation, editing, and extension workflows","context":1024,"output":0,"open_weights":false,"reasoning":false,"tools":false,"input_modalities":["text","image","video"],"output_modalities":["video"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-imagine-video-1.5.toml"},{"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":true,"tools":false,"input_modalities":["text","image","video","pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-image.toml"},{"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":true,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-image.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-8.toml"},{"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":65536,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.7-max.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.5-flash.toml"},{"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":null,"output":0,"open_weights":false,"reasoning":false,"tools":false,"input_modalities":["audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-realtime-whisper.toml"},{"id":"google/gemini-3.1-flash-lite","name":"Gemini 3.1 Flash Lite","lab":"google","date":"2026-05-07","description":"Low-latency Gemini model for high-volume multimodal and agent workloads","context":1048576,"output":65536,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5-instant.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-2604.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-nano-omni-30b-a3b-reasoning.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-flash.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5-pro.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.5.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-pro-0423.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v4-flash-0423.toml"},{"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":false,"tools":false,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-embedding-2.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-27b.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-2.toml"},{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","lab":"moonshotai","date":"2026-04-21","description":"Multimodal Kimi workhorse for agent loops, coding tasks, and visual context","context":262144,"output":262144,"open_weights":true,"reasoning":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2.6.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/deep-research-preview-04-2026.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/deep-research-max-preview-04-2026.toml"},{"id":"alibaba/qwen3.6-max-preview","name":"Qwen3.6 Max Preview","lab":"alibaba","date":"2026-04-20","description":"Flagship Qwen model for complex reasoning, coding, and agentic workflows","context":262144,"output":65536,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-max-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.3.toml"},{"id":"alibaba/qwen3.6-35b-a3b","name":"Qwen3.6 35B-A3B","lab":"alibaba","date":"2026-04-17","description":"Open multimodal Qwen MoE for local agents that need vision, audio, and code","context":262144,"output":65536,"open_weights":true,"reasoning":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-35b-a3b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-build-0.1.toml"},{"id":"nvidia/nemotron-3-content-safety","name":"Nemotron 3 Content Safety","lab":"nvidia","date":"2026-04-16","description":"Safety model for policy screening, moderation, and risk-aware routing workflows","context":128000,"output":4096,"open_weights":true,"reasoning":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-content-safety.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-7.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-tts-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-robotics-er-1.6-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/muse-spark-1.1.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.1.toml"},{"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":true,"tools":true,"input_modalities":["text","image","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-E4B-it.toml"},{"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":true,"tools":true,"input_modalities":["text","image","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-E2B-it.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-31b-it.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-4-26b-a4b-it.toml"},{"id":"alibaba/qwen3.6-plus","name":"Qwen3.6 Plus","lab":"alibaba","date":"2026-04-02","description":"Earlier Qwen multimodal workhorse for million-token agent and document tasks","context":1000000,"output":65536,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.6-plus.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5v-turbo.toml"},{"id":"nvidia/llama-nemotron-rerank-vl-1b-v2","name":"Llama Nemotron Rerank VL 1B v2","lab":"nvidia","date":"2026-03-31","description":"Reranking model for improving retrieval quality in search and recommendation systems","context":128000,"output":4096,"open_weights":true,"reasoning":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-nemotron-rerank-vl-1b-v2.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["video"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-lite-generate-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text","audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-live-preview.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-3-pro-preview.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/lyria-3-clip-preview.toml"},{"id":"nvidia/nemotron-cascade-2-30b-a3b","name":"Nemotron Cascade 2 30B A3B","lab":"nvidia","date":"2026-03-24","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":256000,"output":32768,"open_weights":true,"reasoning":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-cascade-2-30b-a3b.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-nano.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-mini.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5-turbo.toml"},{"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":false,"tools":true,"input_modalities":["text","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-voicechat.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-2603.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-super-120b-a12b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.20-0309-reasoning.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.20-0309-non-reasoning.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4-pro.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.4.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-lite-preview.toml"},{"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":true,"tools":false,"input_modalities":["text","image","pdf"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-flash-image-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-9b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-35b-a3b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-27b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-122b-a10b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-pro-preview-customtools.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3.1-pro-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-6.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-plus.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3.5-397b-a17b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-5.toml"},{"id":"nvidia/llama-nemotron-embed-vl-1b-v2","name":"Llama Nemotron Embed VL 1B v2","lab":"nvidia","date":"2026-02-10","description":"Embedding model for semantic search, retrieval, clustering, and ranking pipelines","context":32768,"output":2048,"open_weights":true,"reasoning":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-nemotron-embed-vl-1b-v2.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.3-codex-spark.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.3-codex.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-6.toml"},{"id":"alibaba/qwen3-coder-next","name":"Qwen3 Coder Next","lab":"alibaba","date":"2026-02-03","description":"Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use","context":262144,"output":65536,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-next.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-ocr-2.toml"},{"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":true,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-content-safety-reasoning-4b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7-flashx.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7-flash.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.7.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-flash-preview.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-3-nano-30b-a3b.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2-pro.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2-codex.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.2.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-small-2.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-2512.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6v-flash.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6v.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-14b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.2.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-1.5.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-5.toml"},{"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":true,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-image-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.1-fast-reasoning.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/xai/grok-4.1-fast.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video","audio","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-3-pro-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex-mini.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex-max.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1-codex.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.1.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-thinking-turbo.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/moonshotai/kimi-k2-thinking.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-safeguard-20b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-safeguard-120b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-nano-12b-v2-vl.toml"},{"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":false,"tools":false,"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"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["video"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-generate-preview.toml"},{"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":false,"tools":false,"input_modalities":["text","image","video"],"output_modalities":["video"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/veo-3.1-fast-generate-preview.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-haiku-4-5.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-computer-use-preview-10-2025.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-pro.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.6.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-pro-tts.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-tts.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-5.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-plus.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-235b-a22b-thinking.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-vl-235b-a22b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-max.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-codex.toml"},{"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":true,"tools":false,"input_modalities":["text","image"],"output_modalities":["text","image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-image.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.1.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-nano-9b-v2.toml"},{"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":true,"tools":true,"input_modalities":["text","image","video"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5v.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-nano.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5-mini.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-5.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-20b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-oss-120b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-1.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5-flash.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5-air.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/zhipuai/glm-4.5.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-flash.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-flash.toml"},{"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":true,"tools":true,"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"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-coder-plus.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-235b-a22b-instruct-2507.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-small-2507.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/devstral-medium-2507.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-2506.toml"},{"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":true,"tools":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-pro.toml"},{"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":true,"tools":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash-lite.toml"},{"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":true,"tools":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.5-flash.toml"},{"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":true,"reasoning":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/mistral-nemotron.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-pro.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/magistral-small-2506.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-sonnet-4-0.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-opus-4-0.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-embedding-001.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-medium-2505.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen3-30b-a3b.toml"},{"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":false,"tools":false,"input_modalities":["text","image"],"output_modalities":["image"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-image-1.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o4-mini.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.1-nemotron-70b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1-nano.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1-mini.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.1.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/pixtral-large-2502.toml"},{"id":"nvidia/llama-3.3-nemotron-super-49b-v1","name":"Llama 3.3 Nemotron Super 49B v1","lab":"nvidia","date":"2025-04-07","description":"Nemotron model for efficient reasoning, coding, and specialized AI agents","context":131072,"output":131072,"open_weights":true,"reasoning":true,"tools":true,"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"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/llama-3.1-nemotron-ultra-253b.toml"},{"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":3500000,"output":16384,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-4-scout-17b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-4-maverick-17b-instruct.toml"},{"id":"deepseek/deepseek-v3-0324","name":"DeepSeek V3 0324","lab":"deepseek","date":"2025-03-24","description":"March 2025 checkpoint of DeepSeek-V3 with improved reasoning and coding","context":163840,"output":163840,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3-0324.toml"},{"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":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o1-pro.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-small-3-1-24b-instruct-2503.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-4b-it.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-27b-it.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemma-3-12b-it.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwq-plus.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwq-32b.toml"},{"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":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-7-sonnet-20250219.toml"},{"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":true,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1-distill-qwen-32b.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-r1.toml"},{"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":false,"tools":true,"input_modalities":["text","image","audio","video"],"output_modalities":["text","audio"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-omni-turbo.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/deepseek/deepseek-v3.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-mini.toml"},{"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":false,"tools":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.0-flash-lite.toml"},{"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":false,"tools":true,"input_modalities":["text","image","audio","video","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/google/gemini-2.0-flash.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.3-70b-instruct.toml"},{"id":"openai/o1","name":"o1","lab":"openai","date":"2024-12-05","description":"O-series reasoning model for hard analysis, math, coding, and planning","context":200000,"output":100000,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o1.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-2024-11-20.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-2411.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2.5-coder-32b-instruct.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen2.5-coder-0.5b.toml"},{"id":"mistral/mistral-large-2512","name":"Mistral Large 3","lab":"mistral","date":"2024-11-01","description":"Mistral's largest general model for enterprise agents, coding, and multilingual reasoning","context":262144,"output":262144,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-large-2512.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-turbo.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-5-sonnet-20241022.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-5-haiku-20241022.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-8b-instruct-2410.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/ministral-3b.toml"},{"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":false,"tools":false,"input_modalities":["audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/whisper-large-v3-turbo.toml"},{"id":"openai/whisper-large-v3","name":"Whisper 3 Large","lab":"openai","date":"2024-10-01","description":"Open Whisper checkpoint for robust multilingual transcription and captioning","context":448,"output":4096,"open_weights":true,"reasoning":false,"tools":false,"input_modalities":["audio"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/whisper-large-v3.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-3b.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.2-1b.toml"},{"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":false,"tools":true,"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"},{"id":"mistral/pixtral-12b","name":"Pixtral 12B","lab":"mistral","date":"2024-09-01","description":"Mistral vision-language model for image understanding and multimodal chat","context":128000,"output":128000,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/pixtral-12b.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/nvidia/nemotron-mini-4b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-2024-08-06.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-guard-3-8b.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.1-8b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/meta/llama-3.1-70b-instruct.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o-mini.toml"},{"id":"mistral/mistral-nemo","name":"Mistral Nemo","lab":"mistral","date":"2024-07-01","description":"Efficient Mistral-NVIDIA open model for multilingual chat and local deployment","context":128000,"output":128000,"open_weights":true,"reasoning":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/mistral-nemo.toml"},{"id":"openai/o4-mini-deep-research","name":"o4-mini-deep-research","lab":"openai","date":"2024-06-26","description":"Research model for long-horizon investigation, synthesis, and analytical reports","context":200000,"output":100000,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o4-mini-deep-research.toml"},{"id":"openai/o3-deep-research","name":"o3-deep-research","lab":"openai","date":"2024-06-26","description":"Research model for long-horizon investigation, synthesis, and analytical reports","context":200000,"output":100000,"open_weights":false,"reasoning":true,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/o3-deep-research.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/mistral/codestral-22b-v0.1.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4o.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-vl-max.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-max.toml"},{"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":false,"tools":true,"input_modalities":["text","image","pdf"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/anthropic/claude-3-haiku-20240307.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-vl-plus.toml"},{"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":true,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/alibaba/qwen-plus.toml"},{"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":false,"tools":true,"input_modalities":["text","image"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4-turbo.toml"},{"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":false,"tools":true,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-4.toml"},{"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":false,"tools":false,"input_modalities":["text"],"output_modalities":["text"],"source":"https://github.com/anomalyco/models.dev/blob/dev/models/openai/gpt-3.5-turbo.toml"}]}