Qwen3.5 397B A17B

qwen/qwen3.5-397b-a17b-20260216

Qwen3.5 397B A17B is a model from qwen that accepts text, image, and video inputs and produces text output. It supports tool use and reasoning, provides a context length of 262 144 tokens, and its weights are not open. Pricing is $0.39 per million input tokens and $2.34 per million output tokens; the model was released on 2026‑02‑15.

  • tool use
  • structured outputs
  • reasoning

At a glance

providerqwen
releasedFeb 15, 2026
context262K
input / M$0.39

Specifications

What the API gives you

Context window
262K tokens
Max output
66K tokens
Input price
$0.39 / 1M tokens
Output price
$2.34 / 1M tokens
Cache read
Modalities
text, image, video → text
Knowledge cutoff
Released
Feb 15, 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
1438 Elo2026-07-16
LMArena Vision
1267 Elo2026-07-12
LMArena WebDev
1396 Elo2026-07-16
LMArena WebDev
1396 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.