GPT-5.1 Mini: pricing, context window and benchmarks
GPT-5.1 Mini is a multimodal model from OpenAI. It offers a 128,000-token context window, costs $12.19 per million input tokens and $44.14 per million output tokens, and averages 77.7 across the index's benchmark suite.
Pricing
GPT-5.1 Mini costs $12.19 per million input tokens and $44.14 per million output tokens. A blended 3:1 input-to-output mix works out to about $20.18 per million tokens. Cached input is listed at $1.05 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $12.19 | per 1M tokens |
| Output | $44.14 | per 1M tokens |
| Cached input | $1.05 | per 1M tokens |
| Blended 3:1 | $20.18 | estimate per 1M tokens |
| 1M in + 1M out | $56.33 | 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 | 79.1 | 205 | 66th | |
| GPQA Diamond | 71.4 | 231 | 62th | |
| SWE-bench Verified | 66.3 | 184 | 69th | |
| HumanEval | 80.5 | 219 | 64th | |
| MATH-500 | 79.9 | 210 | 65th | |
| AIME 2025 | 71.5 | 226 | 62th | |
| LiveCodeBench | 71.0 | 172 | 71th | |
| IFEval | 86.8 | 138 | 77th | |
| TruthfulQA | 82.4 | 120 | 80th | |
| HellaSwag | 88.8 | 118 | 80th | |
| MMMU | 76.6 | 120 | 80th | |
| Arena Elo | 1422.9 | 135 | 78th |
What GPT-5.1 Mini is good for
GPT-5.1 Mini 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 $12.19 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 128,000-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 $12.19 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| MiniMax-Text Chat | MiniMax | 128000 | $4.26 | 77.8 |
| Sonar Max | Perplexity | 32768 | $11.60 | 77.8 |
| DeepSeek-Coder Instruct | DeepSeek | 32768 | $4.34 | 77.7 |
| GPT-5.1 Mini | OpenAI | 128000 | $12.19 | 77.7 |
| MiniMax-Text Instruct | MiniMax | 128000 | $4.59 | 77.7 |
| o4 Mini | OpenAI | 200000 | $11.92 | 77.7 |
FAQ
How much does GPT-5.1 Mini cost?
GPT-5.1 Mini is listed at $12.19 per million input tokens and $44.14 per million output tokens. Cached input is $1.05 per million tokens. A blended 3:1 input-to-output mix is about $20.18 per million tokens.
What is the context window of GPT-5.1 Mini?
GPT-5.1 Mini has a context window of 128,000 tokens and can emit up to 32,768 output tokens per request in this index.
Is GPT-5.1 Mini open weights?
No. GPT-5.1 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.1 Mini score on benchmarks?
GPT-5.1 Mini averages 77.7 across the scored benchmarks in this index, ranking #180 of 600 models. Its strongest relative result is Arena Elo at 1422.9.
What is GPT-5.1 Mini best for?
GPT-5.1 Mini 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 $12.19 per million input tokens, it sits in the mid-range of the index, and the 128,000-token context window is enough for large files and multi-file diffs.