qwen
Qwen2.5 Coder 32B Instruct
qwen/qwen-2.5-coder-32b-instruct
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Qwen2.5 Coder 32B Instruct is an instruction-tuned, code-focused causal language model from Qwen, derived from the Qwen2.5-Coder-32B base and trained on 5.5 trillion tokens. Its model card reports gains in code generation, reasoning, and fixing over CodeQwen1.5 while retaining mathematics and general capabilities. It processes text only, ships with a 32,768-token default context, and can reach 128K tokens via YaRN scaling. Vendor claims, including GPT-4o-level coding, were not independently verified in this source pack.[1][2]
Strengths
- The vendor reports strong code generation, code reasoning, and code-fixing ability, built on 5.5 trillion training tokens including source code and synthetic data.[2]
- Text-in, text-out chat model with broad OpenRouter sampling controls such as temperature, top_p, top_k, seed, stop, and response_format.[1]
- Long-context support up to 131,072 tokens via YaRN rope scaling, beyond the 32,768-token default configuration.[2]
Limitations
- No independent evaluation data was available in this source pack; OpenRouter lists no benchmark results, so vendor claims such as GPT-4o-level coding remain unverified and need workload validation.[1][2]
- OpenRouter exposes the model at 32,768 tokens of context; reaching 128K requires YaRN configuration, which the card warns can reduce performance on shorter texts.[1][2]
- Text-only input and output, English is the only listed language, and the knowledge cutoff is 2024-06-30.[1][2]
Where to use it
- Editorial suggestion: code generation, completion, and bug-fixing assistance, matching the vendor's stated design goals.[2]
- Editorial suggestion: code-agent workflows, which the model card names as a target application area.[2]
- Editorial suggestion: long-context code analysis for teams willing to enable YaRN scaling, subject to their own validation.[2]
Sources
- [1] OpenRouter catalog · Qwen2.5 Coder 32B InstructSources checked: Nov 13, 2026
- [2] Model documentation · Qwen2.5 Coder 32B InstructSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...
Specifications
- Model ID
- qwen/qwen-2.5-coder-32b-instruct
- Creator
- qwen
- Added to OpenRouter
- 11.11.2024
- Context length
- 32,768
- Modality
- text->text
- Input modalities
- text
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.660 / out $1
- Knowledge cutoff
- 30.06.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | No measurement | — |
| Agents | No measurement | — |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | — |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
No evaluations are supplied for this model.
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Cloudflare | 32,768 | $0.660 | $1 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.