qwen

Qwen2.5 Coder 32B Instruct

The Qwen2.5 Coder 32B Instruct is a text-based AI model developed by qwen. It processes input in the form of text and provides output within the same modality. The model's context length is set at 32,768 tokens, allowing it to handle extended passages or complex conversations. This model may be worth considering for users who prioritize text-based tasks and have a moderate budget. With an input price per million tokens (MTOK) of $0.66 and an output price per MTOK of $1.00, the Qwen2.5 Coder 32B Instruct offers relatively affordable processing capabilities. Its blended benchmark score of 15.2 across one independent benchmark suggests a competitive performance level, making it a viable option for those seeking a balance between cost and quality.

Open weights 32.5B parameters, about 18.2 GiB at Q4_K_M: fits comfortably on 4 of 18 consumer graphics cards in the PicksByCard catalog. See which cards run it →
Quality Score
63/100
price + capability + benchmarks
Input Price
$0.66
per 1M tokens · checked 2026-09-23
Output Price
$1.00
per 1M tokens · checked 2026-09-23
Context Window
32,768
tokens

Benchmark results

Independent, published benchmarks. Blended score 15.2 across 1 benchmark, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
Aider Polyglot code editing across languages 16.4
Model ID
qwen/qwen-2.5-coder-32b-instruct
Vendor
qwen
Released
November 2024
Tokenizer
Qwen
Input Modalities
text
Output Modalities
text
Max Output
29,491 tokens
Tool Calling
not supported
Structured Output
✓ supported
Reasoning Mode
not supported
Vision
text only
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.66/M input and $1.00/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out $0.02
Classify 1,000 customer emails 500k in / 50k out $0.38
A month of a busy support chatbot 5M in / 2M out $5.30

Price & spec history

Tracked daily by PicksByModel since 2026-07-17.

DateInput /MOutput /MContext
2026-07-22 $0.66 $1.00 32,768
2026-07-17 $0.66 $1.00 128,000

Similar models

Quick answers

How much does Qwen2.5 Coder 32B Instruct cost?
$0.66 per million input tokens and $1.00 per million output tokens.
What is Qwen2.5 Coder 32B Instruct's context window?
32,768 tokens, roughly 49 pages of text in a single request.
Does Qwen2.5 Coder 32B Instruct support tool calling?
It supports structured output.
Can Qwen2.5 Coder 32B Instruct process images?
No, it is text-only on the input side.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.