Qwen3-Coder Chat: pricing, context window and benchmarks
Qwen3-Coder Chat is a coding model from Alibaba Cloud. It offers a 128,000-token context window, costs $4.59 per million input tokens and $21.05 per million output tokens, and averages 78.4 across the index's benchmark suite.
Pricing
Qwen3-Coder Chat costs $4.59 per million input tokens and $21.05 per million output tokens. A blended 3:1 input-to-output mix works out to about $8.71 per million tokens. Cached input is listed at $0.44 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $4.59 | per 1M tokens |
| Output | $21.05 | per 1M tokens |
| Cached input | $0.44 | per 1M tokens |
| Blended 3:1 | $8.71 | estimate per 1M tokens |
| 1M in + 1M out | $25.64 | 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 | 79.4 | 201 | 67th | |
| GPQA Diamond | 72.4 | 213 | 65th | |
| SWE-bench Verified | 69.5 | 122 | 80th | |
| HumanEval | 82.9 | 161 | 73th | |
| MATH-500 | 85.2 | 106 | 82th | |
| AIME 2025 | 74.0 | 183 | 70th | |
| LiveCodeBench | 68.9 | 211 | 65th | |
| IFEval | 85.0 | 193 | 68th | |
| TruthfulQA | 81.3 | 146 | 76th | |
| HellaSwag | 88.0 | 142 | 76th | |
| MMMU | 76.2 | 135 | 78th | |
| Arena Elo | 1411.0 | 182 | 70th |
What Qwen3-Coder Chat is good for
Qwen3-Coder Chat 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 $4.59 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 |
|---|---|---|---|---|
| GLM-4.6 Base | Zhipu AI | 128000 | $4.53 | 78.5 |
| Reka Core Reasoning | Reka AI | 32768 | $13.11 | 78.5 |
| Magistral Instruct | Mistral AI | 65536 | $4.48 | 78.4 |
| Nova Pro Turbo | Amazon | 128000 | $13.18 | 78.4 |
| Qwen3-Coder Chat | Alibaba Cloud | 128000 | $4.59 | 78.4 |
| Reka Core Turbo | Reka AI | 32768 | $12.58 | 78.4 |
FAQ
How much does Qwen3-Coder Chat cost?
Qwen3-Coder Chat is listed at $4.59 per million input tokens and $21.05 per million output tokens. Cached input is $0.44 per million tokens. A blended 3:1 input-to-output mix is about $8.71 per million tokens.
What is the context window of Qwen3-Coder Chat?
Qwen3-Coder Chat has a context window of 128,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Qwen3-Coder Chat open weights?
Yes. Qwen3-Coder Chat is listed as an open-weight model under a open weights licence.
How does Qwen3-Coder Chat score on benchmarks?
Qwen3-Coder Chat averages 78.4 across the scored benchmarks in this index, ranking #159 of 600 models. Its strongest relative result is Arena Elo at 1411.0.
What is Qwen3-Coder Chat best for?
Qwen3-Coder Chat 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 $4.59 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.