GPT-4.1 Max: pricing, context window and benchmarks
GPT-4.1 Max is a frontier model from OpenAI. It offers a 400,000-token context window, costs $17.34 per million input tokens and $66.38 per million output tokens, and averages 84.7 across the index's benchmark suite.
Pricing
GPT-4.1 Max costs $17.34 per million input tokens and $66.38 per million output tokens. A blended 3:1 input-to-output mix works out to about $29.60 per million tokens. Cached input is listed at $1.42 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.34 | per 1M tokens |
| Output | $66.38 | per 1M tokens |
| Cached input | $1.42 | per 1M tokens |
| Blended 3:1 | $29.60 | estimate per 1M tokens |
| 1M in + 1M out | $83.72 | 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 | 87.4 | 26 | 96th | |
| GPQA Diamond | 81.2 | 42 | 93th | |
| SWE-bench Verified | 74.8 | 42 | 93th | |
| HumanEval | 88.8 | 59 | 90th | |
| MATH-500 | 87.3 | 73 | 88th | |
| AIME 2025 | 84.9 | 40 | 93th | |
| LiveCodeBench | 78.5 | 59 | 90th | |
| IFEval | 92.1 | 37 | 94th | |
| TruthfulQA | 85.4 | 61 | 90th | |
| HellaSwag | 90.7 | 69 | 89th | |
| MMMU | 80.5 | 51 | 92th | |
| Arena Elo | 1467.6 | 39 | 94th |
What GPT-4.1 Max is good for
GPT-4.1 Max 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 $17.34 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 (84.7), placing it #51 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 $17.34 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GPT-5.1 Vision | OpenAI | 400000 | $17.76 | 84.8 |
| Gemini 2.5 Pro Max | Google DeepMind | 200000 | $16.94 | 84.8 |
| Gemini 3 Flash Pro | Google DeepMind | 400000 | $17.71 | 84.8 |
| o3 Max | OpenAI | 2000000 | $17.82 | 84.8 |
| GPT-4.1 Max | OpenAI | 400000 | $17.34 | 84.7 |
| Qwen3-Max Turbo | Alibaba Cloud | 1000000 | $17.70 | 84.7 |
FAQ
How much does GPT-4.1 Max cost?
GPT-4.1 Max is listed at $17.34 per million input tokens and $66.38 per million output tokens. Cached input is $1.42 per million tokens. A blended 3:1 input-to-output mix is about $29.60 per million tokens.
What is the context window of GPT-4.1 Max?
GPT-4.1 Max has a context window of 400,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is GPT-4.1 Max open weights?
No. GPT-4.1 Max is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-4.1 Max score on benchmarks?
GPT-4.1 Max averages 84.7 across the scored benchmarks in this index, ranking #51 of 600 models. Its strongest relative result is Arena Elo at 1467.6.
What is GPT-4.1 Max best for?
GPT-4.1 Max 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 $17.34 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.