Qwen
EfficientPriced via OpenRouter

Qwen2.5 Coder 32B Instruct

text->text

Best open-weights code model in its class. A strong Codestral / GPT-4 alternative for self-hosted IDE backends.

Qwen2.5 Coder 32B Instruct is a efficient AI model from Qwen. It costs $0.6600 per million input tokens and $1.00 per million output tokens (blended $0.7620/M), with a 32,768-token context window.

Profile inherited from upstream Qwen2.5-Coder-32B ↗ — this is a hosted variant of the same open-weights model.

RatesUSD per million tokens. Blend is 70% input, 30% output, our calculation.

INPUT
$0.6600/M
per million input tokens
OUTPUT
$1.00/M
per million output tokens
BLENDED 70/30
$0.7620/M
unchanged since 3 May
CONTEXT
32,768
tokens

From OpenRouter's listing, read on 17 Nov 2026.

What it is good at
  • Best open-weights code at 32B
  • 128K context
  • Permissive license
Typical use cases
  • Self-hosted IDE backends
  • Code review bots

Benchmarks

vs. best public score
Scores inherited from Qwen2.5-Coder-32B — this is a hosted variant of the same open-weights model, so the underlying benchmark scores are identical.
MMLU77.6%
Multitask academic knowledge across 57 subjects. Source: Alibaba (Qwen team) (self-reported), MMLU, read 2026-11-10.
HumanEval92.7%
Python function synthesis from docstrings. Source: Alibaba (Qwen team) (self-reported), HumanEval, read 2026-11-10.
LMArena Elo1271 Elo
Crowd-sourced head-to-head preference Elo rating. Source: LMArena (independent), LMArena Text Arena score, read 2026-11-10.
Hand-curated from each provider's published reports and public leaderboards. Methodology varies across sources, treat as directional rather than authoritative.

More from Qwen

See all 22 →

Frequently asked questions

How much does Qwen2.5 Coder 32B Instruct cost?

Qwen2.5 Coder 32B Instruct costs $0.6600 per million input tokens and $1.00 per million output tokens, for a blended reference rate of $0.7620 per million tokens.

What is Qwen2.5 Coder 32B Instruct's context window?

Qwen2.5 Coder 32B Instruct supports up to 32,768 tokens of context in a single request.

What is Qwen2.5 Coder 32B Instruct best for?

Qwen2.5 Coder 32B Instruct is well suited to Best open-weights code at 32B, 128K context and Permissive license.

Who makes Qwen2.5 Coder 32B Instruct?

Qwen2.5 Coder 32B Instruct is developed and served by Qwen.

Terms used on this page