Qwen3: pricing, context window and benchmarks
Qwen3 is a multimodal model from Alibaba Cloud. It offers a 128,000-token context window, costs $5.04 per million input tokens and $22.52 per million output tokens, and averages 80.3 across the index's benchmark suite.
Pricing
Qwen3 costs $5.04 per million input tokens and $22.52 per million output tokens. A blended 3:1 input-to-output mix works out to about $9.41 per million tokens. Cached input is listed at $0.57 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $5.04 | per 1M tokens |
| Output | $22.52 | per 1M tokens |
| Cached input | $0.57 | per 1M tokens |
| Blended 3:1 | $9.41 | estimate per 1M tokens |
| 1M in + 1M out | $27.56 | 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 | 81.2 | 143 | 76th | |
| GPQA Diamond | 77.7 | 94 | 84th | |
| SWE-bench Verified | 71.6 | 83 | 86th | |
| HumanEval | 87.0 | 89 | 85th | |
| MATH-500 | 86.5 | 85 | 86th | |
| AIME 2025 | 74.5 | 166 | 72th | |
| LiveCodeBench | 73.8 | 114 | 81th | |
| IFEval | 85.6 | 170 | 72th | |
| TruthfulQA | 80.4 | 168 | 72th | |
| HellaSwag | 88.1 | 139 | 77th | |
| MMMU | 76.7 | 119 | 80th | |
| Arena Elo | 1420.9 | 145 | 76th |
What Qwen3 is good for
Qwen3 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 $5.04 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 |
|---|---|---|---|---|
| Qwen3 | Alibaba Cloud | 128000 | $5.04 | 80.3 |
| DeepSeek-V3.2 Base | DeepSeek | 128000 | $5.05 | 80.2 |
| Doubao 1.5 Pro Pro | ByteDance | 128000 | $14.10 | 80.2 |
| GLM-4.6 | Zhipu AI | 128000 | $5.10 | 80.2 |
| Kimi K1.5 Chat | Moonshot AI | 128000 | $5.11 | 80.2 |
| MiniMax-M2 Chat | MiniMax | 200000 | $5.02 | 80.2 |
FAQ
How much does Qwen3 cost?
Qwen3 is listed at $5.04 per million input tokens and $22.52 per million output tokens. Cached input is $0.57 per million tokens. A blended 3:1 input-to-output mix is about $9.41 per million tokens.
What is the context window of Qwen3?
Qwen3 has a context window of 128,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Qwen3 open weights?
Yes. Qwen3 is listed as an open-weight model under a open weights licence.
How does Qwen3 score on benchmarks?
Qwen3 averages 80.3 across the scored benchmarks in this index, ranking #111 of 600 models. Its strongest relative result is Arena Elo at 1420.9.
What is Qwen3 best for?
Qwen3 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 $5.04 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.