Qwen3-Max Pro: pricing, context window and benchmarks
Qwen3-Max Pro is a frontier model from Alibaba Cloud. It offers a 400,000-token context window, costs $18.87 per million input tokens and $84.39 per million output tokens, and averages 86.2 across the index's benchmark suite.
Pricing
Qwen3-Max Pro costs $18.87 per million input tokens and $84.39 per million output tokens. A blended 3:1 input-to-output mix works out to about $35.25 per million tokens. Cached input is listed at $2.20 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $18.87 | per 1M tokens |
| Output | $84.39 | per 1M tokens |
| Cached input | $2.20 | per 1M tokens |
| Blended 3:1 | $35.25 | estimate per 1M tokens |
| 1M in + 1M out | $103.26 | 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 | 88.7 | 11 | 98th | |
| GPQA Diamond | 80.0 | 58 | 90th | |
| SWE-bench Verified | 75.6 | 34 | 94th | |
| HumanEval | 92.1 | 20 | 97th | |
| MATH-500 | 91.8 | 27 | 96th | |
| AIME 2025 | 85.4 | 35 | 94th | |
| LiveCodeBench | 81.0 | 32 | 95th | |
| IFEval | 93.2 | 20 | 97th | |
| TruthfulQA | 88.6 | 17 | 97th | |
| HellaSwag | 92.4 | 36 | 94th | |
| MMMU | 79.5 | 67 | 89th | |
| Arena Elo | 1466.4 | 42 | 93th |
What Qwen3-Max Pro is good for
Qwen3-Max Pro sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $18.87 per million input tokens and a 400,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.
Strengths
- Top-tier average benchmark score (86.2), placing it #28 of 600.
- Large 400,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- Coding benchmarks are a relative strength within its tier.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $18.87 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Gemini 3 Pro Turbo | Google DeepMind | 400000 | $19.62 | 86.4 |
| Qwen3-Max Pro | Alibaba Cloud | 400000 | $18.87 | 86.2 |
| o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
| GPT-5.1 Turbo | OpenAI | 2000000 | $19.19 | 86.1 |
| Gemini 3 Pro | Google DeepMind | 2000000 | $18.24 | 86.1 |
| GPT-5.1 | OpenAI | 2000000 | $19.01 | 86.0 |
FAQ
How much does Qwen3-Max Pro cost?
Qwen3-Max Pro is listed at $18.87 per million input tokens and $84.39 per million output tokens. Cached input is $2.20 per million tokens. A blended 3:1 input-to-output mix is about $35.25 per million tokens.
What is the context window of Qwen3-Max Pro?
Qwen3-Max Pro has a context window of 400,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is Qwen3-Max Pro open weights?
No. Qwen3-Max Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Qwen3-Max Pro score on benchmarks?
Qwen3-Max Pro averages 86.2 across the scored benchmarks in this index, ranking #28 of 600 models. Its strongest relative result is Arena Elo at 1466.4.
What is Qwen3-Max Pro best for?
Qwen3-Max Pro sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $18.87 per million input tokens and a 400,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.