Qwen3.5-122B-A10B
qwen/qwen3.5-122b-a10b-20260224
Qwen3.5-122B-A10B, provided by Qwen, accepts text, image, and video inputs and generates text output. It supports tool usage and reasoning, offers open weights, and has a context length of 262,144 tokens. The model was released on 2026-02-26 and is priced at $0.26 per million input tokens and $2.08 per million output tokens.
- tool use
- structured outputs
- reasoning
- open-weight
At a glance
Specifications
What the API gives you
- Context window
- 262K tokens
- Max output
- 66K tokens
- Input price
- $0.26 / 1M tokens
- Output price
- $2.08 / 1M tokens
- Cache read
- —
- Modalities
- text, image, video → text
- Knowledge cutoff
- —
- Released
- Feb 26, 2026
Recommendation coverage
Where this model appears
Not currently included in a published recommendation. This means the available task-specific evidence did not support a ranking yet—not that the model was reviewed and rejected.
Measured evidence
Public benchmark record
- LMArena Text
- 1418 Elo2026-07-16
- LMArena Vision
- 1246 Elo2026-07-12
- LMArena WebDev
- 1364 Elo2026-07-16
- LMArena WebDev
- 1364 Elo2026-07-20
LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open.
Open-weight model on Hugging Face.
Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.