# Qwen3-Coder 30B-A3B Instruct Usage, Cost & Rank | OpenCode Data

> Qwen3-Coder 30B-A3B Instruct costs $0.45 per 1M input tokens and $2.25 per 1M output tokens.

Smaller Qwen coder for efficient local agents and repo-level fixes

- Page: https://opencode.ai/data/alibaba/qwen3-coder-30b-a3b-instruct
- JSON: https://opencode.ai/data/alibaba/qwen3-coder-30b-a3b-instruct.json
- Model ID: alibaba/qwen3-coder-30b-a3b-instruct
- Lab: Alibaba

## Model facts

| Fact | Value |
| --- | --- |
| Context window | 262K |
| Max output | 66K |
| Knowledge cutoff | 2025-04 |
| Release date | 2025-04 |
| Input modalities | text |
| Output modalities | text |
| Reasoning | No |
| Tool calling | Yes |
| Open weights | Yes |
| Weights | [Hugging Face](https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct) |

## Pricing: USD per 1M tokens

| Input | Output | Cached input | Cache write |
| --- | --- | --- | --- |
| $0.45 | $2.25 | - | - |

## Benchmarks

| Benchmark | Score | Metric | Source |
| --- | --- | --- | --- |
| Artificial Analysis Coding Index | 19.4 | index | https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks |
| SciCode | 27.8 | percent correct | https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks |
| Terminal-Bench Hard | 15.2 | success rate | https://openrouter.ai/qwen/qwen3-coder-30b-a3b-instruct/benchmarks |

## 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.