GPT-4.1 Pro: pricing, context window and benchmarks
GPT-4.1 Pro is a frontier model from OpenAI. It offers a 400,000-token context window, costs $17.56 per million input tokens and $91.14 per million output tokens, and averages 85.2 across the index's benchmark suite.
Pricing
GPT-4.1 Pro costs $17.56 per million input tokens and $91.14 per million output tokens. A blended 3:1 input-to-output mix works out to about $35.95 per million tokens. Cached input is listed at $1.84 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.56 | per 1M tokens |
| Output | $91.14 | per 1M tokens |
| Cached input | $1.84 | per 1M tokens |
| Blended 3:1 | $35.95 | estimate per 1M tokens |
| 1M in + 1M out | $108.70 | 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 | 86.9 | 38 | 94th | |
| GPQA Diamond | 78.2 | 81 | 87th | |
| SWE-bench Verified | 77.3 | 21 | 97th | |
| HumanEval | 91.9 | 23 | 96th | |
| MATH-500 | 88.8 | 61 | 90th | |
| AIME 2025 | 82.8 | 56 | 91th | |
| LiveCodeBench | 76.7 | 73 | 88th | |
| IFEval | 92.2 | 34 | 94th | |
| TruthfulQA | 87.7 | 25 | 96th | |
| HellaSwag | 93.7 | 16 | 97th | |
| MMMU | 81.5 | 38 | 94th | |
| Arena Elo | 1449.6 | 73 | 88th |
What GPT-4.1 Pro is good for
GPT-4.1 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 $17.56 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 (85.2), placing it #45 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 $17.56 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 Vision | Google DeepMind | 200000 | $17.59 | 85.5 |
| Grok 4 Pro | xAI | 1000000 | $19.00 | 85.4 |
| o4 | OpenAI | 2000000 | $17.74 | 85.4 |
| o3 Reasoning | OpenAI | 200000 | $18.07 | 85.3 |
| GPT-4.1 Pro | OpenAI | 400000 | $17.56 | 85.2 |
| Gemini 3 Flash Max | Google DeepMind | 1000000 | $17.43 | 85.0 |
FAQ
How much does GPT-4.1 Pro cost?
GPT-4.1 Pro is listed at $17.56 per million input tokens and $91.14 per million output tokens. Cached input is $1.84 per million tokens. A blended 3:1 input-to-output mix is about $35.95 per million tokens.
What is the context window of GPT-4.1 Pro?
GPT-4.1 Pro 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 Pro open weights?
No. GPT-4.1 Pro is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-4.1 Pro score on benchmarks?
GPT-4.1 Pro averages 85.2 across the scored benchmarks in this index, ranking #45 of 600 models. Its strongest relative result is HellaSwag at 93.7.
What is GPT-4.1 Pro best for?
GPT-4.1 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 $17.56 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.