# Qwen2.5-Coder-32B-Instruct Usage, Cost & Rank | OpenCode Data

> Qwen2.5-Coder-32B-Instruct costs $0.29 per 1M input tokens and $0.86 per 1M output tokens.

Open coding-focused Qwen model for code generation, repair, and repository reasoning

- Page: https://opencode.ai/data/alibaba/qwen2-5-coder-32b-instruct
- JSON: https://opencode.ai/data/alibaba/qwen2-5-coder-32b-instruct.json
- Model ID: alibaba/qwen2.5-coder-32b-instruct
- Lab: Alibaba

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 131K |
| Max output | 8.2K |
| Knowledge cutoff | - |
| Release date | 2024-11-12 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/Qwen/Qwen2.5-Coder-32B-Instruct) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.29 | $0.86 | - | - |

## Methodology

- Updates: Aggregated every hour. Days and weeks use UTC.
- Tokens: Input, output, reasoning, and cached tokens for each request.
- Users and sessions: Approximate counts of distinct users and OpenCode sessions.
- Cost: Session cost is the average cost per OpenCode session. Token prices are list prices from the OpenCode model catalog.
- Retention: The share of a model's users in one week who use it again the next week.
- Citation: Cite OpenCode Data (opencode.ai/data) with the update time shown at the top of the page.