Qwen3 VL 30B A3B Instruct
Latest Qwen3 VLOpen vision-language MoE model for image and video understanding, documents, and visual agents
- Price per 1M tokens
- $0.15 / $0.6 input / output · OpenRouter
- Context window
- 262.1K tokens in · 32.8K out
- Since the last one
- 11 days after Qwen3 VL 235B A22B Instruct
Since Qwen3 VL 235B A22B Instruct
2 releases in the Qwen3 VL line.
Released11 days later
Price in / out$0.15 / $0.6−58%
Context262.1K2.0×
BENCHMARKS
Not in the Epoch Capabilities Index. Epoch benchmarks what it can run, so this is a gap in coverage, not a poor result.
Qwen's past year
48 release days in the past year, about one every 8 days. The next is expected around Oct 30, 2026. Forecasts ↗
NovDecJanFebMarAprMayJunJulAugSepOct
Specifications
RELEASE DATEOct 4, 2025
WEIGHTSOpen weights
CONTEXT WINDOW262.1K
MAX OUTPUT32.8K
REASONINGNot listed
TOOL CALLINGNot listed
INPUTStext, image/bmp, image/jpeg, image/png, image/tiff, image/webp, image/heic, video/mp4, video/x-msvideo, video/x-matroska, video/quicktime, video/x-flv, video/x-ms-wmv
OUTPUTStext
Specifications and prices from Models.dev; availability and limits may differ by provider. Benchmarks from Epoch AI (CC BY 4.0), LiveBench and the other sources named above.