Qwen3-Coder Instruct: pricing, context window and benchmarks
Qwen3-Coder Instruct is a coding model from Alibaba Cloud. It offers a 128,000-token context window, costs $4.66 per million input tokens and $24.30 per million output tokens, and averages 78.1 across the index's benchmark suite.
Pricing
Qwen3-Coder Instruct costs $4.66 per million input tokens and $24.30 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.57 per million tokens. Cached input is listed at $0.68 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.66 | per 1M tokens |
| Output | $24.30 | per 1M tokens |
| Cached input | $0.68 | per 1M tokens |
| Blended 3:1 | $9.57 | estimate per 1M tokens |
| 1M in + 1M out | $28.96 | estimate |
Benchmarks
Scores below are modelled estimates on a 0–100 scale. Use them to compare relative position, not as official vendor results.
| Benchmark | Score | Rank | Percentile | Relative |
|---|---|---|---|---|
| MMLU-Pro | 81.5 | 136 | 77th | |
| GPQA Diamond | 71.7 | 228 | 62th | |
| SWE-bench Verified | 69.3 | 126 | 79th | |
| HumanEval | 82.2 | 183 | 70th | |
| MATH-500 | 80.5 | 201 | 67th | |
| AIME 2025 | 72.2 | 216 | 64th | |
| LiveCodeBench | 71.9 | 149 | 75th | |
| IFEval | 85.3 | 180 | 70th | |
| TruthfulQA | 81.0 | 158 | 74th | |
| HellaSwag | 89.4 | 104 | 83th | |
| MMMU | 74.1 | 190 | 68th | |
| Arena Elo | 1418.7 | 154 | 74th |
What Qwen3-Coder Instruct is good for
Qwen3-Coder Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.66 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-token context window for long documents and agent traces.
- Open weights make self-hosting, fine-tuning and data-residency review possible.
- Accepts more than text, including image input where the provider supports it.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- No standout weakness in the indexed specifications, but real-world behaviour still needs testing.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-Coder | DeepSeek | 32768 | $4.55 | 78.1 |
| Gemini 3 Pro Mini | Google DeepMind | 128000 | $12.27 | 78.1 |
| Hunyuan-Large Chat | Tencent | 200000 | $4.35 | 78.1 |
| Qwen3-Coder Instruct | Alibaba Cloud | 128000 | $4.66 | 78.1 |
| ERNIE 4.0 Turbo | Baidu | 65536 | $12.00 | 78.0 |
| Llama 4 Scout Chat | Meta AI | 32768 | $4.66 | 78.0 |
FAQ
How much does Qwen3-Coder Instruct cost?
Qwen3-Coder Instruct is listed at $4.66 per million input tokens and $24.30 per million output tokens. Cached input is $0.68 per million tokens. A blended 3:1 input-to-output mix is about $9.57 per million tokens.
What is the context window of Qwen3-Coder Instruct?
Qwen3-Coder Instruct has a context window of 128,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Qwen3-Coder Instruct open weights?
Yes. Qwen3-Coder Instruct is listed as an open-weight model under a open weights licence.
How does Qwen3-Coder Instruct score on benchmarks?
Qwen3-Coder Instruct averages 78.1 across the scored benchmarks in this index, ranking #172 of 600 models. Its strongest relative result is Arena Elo at 1418.7.
What is Qwen3-Coder Instruct best for?
Qwen3-Coder Instruct is tuned toward coding work. It is a reasonable candidate for code generation, review, debugging and repository-scale tasks, especially when paired with a retrieval layer. At $4.66 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.