GPT-4.1 Vision: pricing, context window and benchmarks
GPT-4.1 Vision is a multimodal model from OpenAI. It offers a 1,000,000-token context window, costs $14.88 per million input tokens and $81.24 per million output tokens, and averages 82.0 across the index's benchmark suite.
Pricing
GPT-4.1 Vision costs $14.88 per million input tokens and $81.24 per million output tokens. A blended 3:1 input-to-output mix works out to about $31.47 per million tokens. Cached input is listed at $1.23 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $14.88 | per 1M tokens |
| Output | $81.24 | per 1M tokens |
| Cached input | $1.23 | per 1M tokens |
| Blended 3:1 | $31.47 | estimate per 1M tokens |
| 1M in + 1M out | $96.12 | 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 | 84.0 | 82 | 86th | |
| GPQA Diamond | 79.3 | 68 | 89th | |
| SWE-bench Verified | 72.4 | 70 | 88th | |
| HumanEval | 86.8 | 92 | 85th | |
| MATH-500 | 87.5 | 71 | 88th | |
| AIME 2025 | 77.2 | 128 | 79th | |
| LiveCodeBench | 74.3 | 102 | 83th | |
| IFEval | 88.7 | 89 | 85th | |
| TruthfulQA | 84.4 | 76 | 87th | |
| HellaSwag | 89.7 | 93 | 85th | |
| MMMU | 77.5 | 106 | 82th | |
| Arena Elo | 1451.8 | 69 | 89th |
What GPT-4.1 Vision is good for
GPT-4.1 Vision 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 $14.88 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 1,000,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- 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 $14.88 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Kimi K2 Instruct | Moonshot AI | 1000000 | $5.80 | 82.3 |
| Kimi K2 Chat | Moonshot AI | 400000 | $5.74 | 82.1 |
| GPT-4.1 Vision | OpenAI | 1000000 | $14.88 | 82.0 |
| Gemini 2.5 Pro Vision | Google DeepMind | 200000 | $14.91 | 82.0 |
| Gemini 3 Flash Vision | Google DeepMind | 400000 | $15.06 | 81.9 |
| o3 Vision | OpenAI | 1000000 | $15.24 | 81.8 |
FAQ
How much does GPT-4.1 Vision cost?
GPT-4.1 Vision is listed at $14.88 per million input tokens and $81.24 per million output tokens. Cached input is $1.23 per million tokens. A blended 3:1 input-to-output mix is about $31.47 per million tokens.
What is the context window of GPT-4.1 Vision?
GPT-4.1 Vision has a context window of 1,000,000 tokens and can emit up to 8,192 output tokens per request in this index.
Is GPT-4.1 Vision open weights?
No. GPT-4.1 Vision is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-4.1 Vision score on benchmarks?
GPT-4.1 Vision averages 82.0 across the scored benchmarks in this index, ranking #85 of 600 models. Its strongest relative result is Arena Elo at 1451.8.
What is GPT-4.1 Vision best for?
GPT-4.1 Vision 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 $14.88 per million input tokens, it sits in the mid-range of the index, and the 1,000,000-token context window is enough for large files and multi-file diffs.