Qwen3 Coder 30B A3B Instruct
Provider: Alibaba (Qwen) CN
Overview
Alibaba's 30.5B MoE coding specialist targets repository-scale generation and agentic tool use with function-calling support.
Strengths
- 128 experts with 8 active per pass
- 262,144 token context window size
- 235,929 token maximum output limit
- Knowledge cutoff date of June 2025
Best use cases
- Large codebase refactoring and analysis
- Agentic workflows with function calling
- Automated multi-file code generation
Pricing position
Matches GPT-4o-mini and Gemma 4 26B at $0.15 input and $0.60 output per million tokens, but costs double the 30B A3B Instruct 2507 variant.
Caveats
No free tier is available, and output pricing exceeds the Qwen3 Next 80B model's $1.10 rate relative to its lower input cost.
Notes drafted by an LLM from the figures on this page (2026-11-15) and rewritten when the price changes.
Key facts
- Price basis
- Median third-party host price (no first-party API)
- Max output
- 236K tokens
- Knowledge cutoff
- 2025-06-30
- Listed on OpenRouter
- 2025-07-31
- Tracked since
- 2026-05-08
- Last updated
- 2026-11-15
Features
Price history
- 2026-11-15 Price change $0.07 / $0.28 → $0.15 / $0.60
Monthly cost estimate
| Scale | Input (M) | Output (M) | Monthly |
|---|---|---|---|
| 0.1M (hobby) | 0.1 | 0.05 | $0.04 |
| 1M (small app) | 1 | 0.5 | $0.45 |
| 10M (mid scale) | 10 | 5 | $4.50 |
| 100M (large) | 100 | 50 | $45.00 |
※ Cache and batch discounts not factored in. Detailed calculator
Official resources
Other models from Alibaba (Qwen)
Similar-priced models
Source: OpenRouter API (qwen/qwen3-coder-30b-a3b-instruct)