Qwen: Qwen3 Coder 30B A3B Instruct
Qwen is an AI model developed by qwen that handles text inputs with a maximum context length of 262144 tokens and supports up to 235929 completion tokens. It can only process text inputs, which limits its versatility compared to models that support multiple input modalities. The Qwen model may be worth considering for users who prioritize text-based applications and have the budget to afford it. At $0.07 per million input tokens and $0.28 per million output tokens, it is a more expensive option than some other models, but its blended benchmark score of 11.7 across one independent benchmark suggests that it can produce competitive results.
Benchmark results
Independent, published benchmarks. Blended score 11.7 across 1 benchmark, last refreshed 2026-09-08. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 15.8 |
- Model ID
- qwen/qwen3-coder-30b-a3b-instruct
- Vendor
- qwen
- Released
- July 2025
- Tokenizer
- Qwen3
- Input Modalities
- text
- Output Modalities
- text
- Max Output
- 235,929 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- text only
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.07/M input and $0.28/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.05 |
| A month of a busy support chatbot | 5M in / 2M out | $0.91 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-11 | $0.07 | $0.28 | 262,144 |
| 2026-08-04 | $0.07 | $0.27 | 262,144 |
| 2026-08-01 | $0.07 | $0.28 | 262,144 |
| 2026-07-22 | $0.07 | $0.27 | 262,144 |
| 2026-07-17 | $0.07 | $0.27 | 160,000 |
Similar models
Qwen: Qwen3 235B A22B Instruct 2507
Qwen: Qwen3 30B A3B Instruct 2507
Qwen: Qwen3 Coder Next
Qwen: Qwen Plus 0728
Qwen: Qwen-Plus
Qwen: Qwen3 Coder Flash
Quick answers
- How much does Qwen: Qwen3 Coder 30B A3B Instruct cost?
- $0.07 per million input tokens and $0.28 per million output tokens.
- What is Qwen: Qwen3 Coder 30B A3B Instruct's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Qwen: Qwen3 Coder 30B A3B Instruct support tool calling?
- It supports tool calling, structured output.
- Can Qwen: Qwen3 Coder 30B A3B Instruct process images?
- No, it is text-only on the input side.