Qwen3 32B

qwen/qwen3-32b-04-28

Qwen: Qwen3 32B is a text‑only language model from the provider qwen that supports text input and output. It offers a context window of 131 072 tokens, supports tools and reasoning, and provides open weights; pricing is $0.08 per million input tokens and $0.28 per million output tokens. The model was released on 2024‑12‑01.

  • tool use
  • structured outputs
  • reasoning
  • open-weight

At a glance

providerqwen
releasedDec 1, 2024
context131K
input / M$0.080

Specifications

What the API gives you

Context window
131K tokens
Max output
16K tokens
Input price
$0.080 / 1M tokens
Output price
$0.28 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Mar 31, 2025
Released
Dec 1, 2024

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

Aider Polyglot
40%2026-07-17
Aider Polyglot
40%2026-07-21

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.