Qwen2.5 Coder 32B Instruct

qwen/qwen-2.5-coder-32b-instruct

Qwen2.5 Coder 32B Instruct is a text-only model from the Qwen provider released on 2024‑11‑01, with open weights. It supports a context length of 128,000 tokens and is priced at $0.66 per M input tokens and $1.00 per M output tokens. The model does not support tool usage or reasoning.

  • open-weight

At a glance

providerqwen
releasedNov 1, 2024
context128K
input / M$0.66

Specifications

What the API gives you

Context window
128K tokens
Max output
33K tokens
Input price
$0.66 / 1M tokens
Output price
$1 / 1M tokens
Cache read
Modalities
text → text
Knowledge cutoff
Jun 30, 2024
Released
Nov 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
16.4%2026-07-17
Aider Polyglot
16.4%2026-07-21
SWE-bench Verified
47%2025-06-16

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Self-reported scaffold plus model result. Treat it as a claim, not an independent measurement.

Open-weight model on Hugging Face.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.