GPT-5.1 Vision: pricing, context window and benchmarks
GPT-5.1 Vision is a frontier model from OpenAI. It offers a 400,000-token context window, costs $17.76 per million input tokens and $80.59 per million output tokens, and averages 84.8 across the index's benchmark suite.
Pricing
GPT-5.1 Vision costs $17.76 per million input tokens and $80.59 per million output tokens. A blended 3:1 input-to-output mix works out to about $33.47 per million tokens. Cached input is listed at $2.41 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.76 | per 1M tokens |
| Output | $80.59 | per 1M tokens |
| Cached input | $2.41 | per 1M tokens |
| Blended 3:1 | $33.47 | estimate per 1M tokens |
| 1M in + 1M out | $98.35 | 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 | 85.5 | 58 | 90th | |
| GPQA Diamond | 78.7 | 74 | 88th | |
| SWE-bench Verified | 73.6 | 59 | 90th | |
| HumanEval | 89.6 | 55 | 91th | |
| MATH-500 | 89.1 | 58 | 90th | |
| AIME 2025 | 82.4 | 60 | 90th | |
| LiveCodeBench | 77.8 | 67 | 89th | |
| IFEval | 92.7 | 24 | 96th | |
| TruthfulQA | 86.9 | 40 | 93th | |
| HellaSwag | 92.1 | 41 | 93th | |
| MMMU | 83.9 | 14 | 98th | |
| Arena Elo | 1462.4 | 47 | 92th |
What GPT-5.1 Vision is good for
GPT-5.1 Vision 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 $17.76 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 (84.8), placing it #47 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 $17.76 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-5.1 Vision cost?
GPT-5.1 Vision is listed at $17.76 per million input tokens and $80.59 per million output tokens. Cached input is $2.41 per million tokens. A blended 3:1 input-to-output mix is about $33.47 per million tokens.
What is the context window of GPT-5.1 Vision?
GPT-5.1 Vision has a context window of 400,000 tokens and can emit up to 16,384 output tokens per request in this index.
Is GPT-5.1 Vision open weights?
No. GPT-5.1 Vision is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.1 Vision score on benchmarks?
GPT-5.1 Vision averages 84.8 across the scored benchmarks in this index, ranking #47 of 600 models. Its strongest relative result is Arena Elo at 1462.4.
What is GPT-5.1 Vision best for?
GPT-5.1 Vision 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 $17.76 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.