GPT-5.2 Mini: pricing, context window and benchmarks
GPT-5.2 Mini is a multimodal model from OpenAI. It offers a 200,000-token context window, costs $13.34 per million input tokens and $49.98 per million output tokens, and averages 80.4 across the index's benchmark suite.
Pricing
GPT-5.2 Mini costs $13.34 per million input tokens and $49.98 per million output tokens. A blended 3:1 input-to-output mix works out to about $22.50 per million tokens. Cached input is listed at $1.98 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $13.34 | per 1M tokens |
| Output | $49.98 | per 1M tokens |
| Cached input | $1.98 | per 1M tokens |
| Blended 3:1 | $22.50 | estimate per 1M tokens |
| 1M in + 1M out | $63.32 | 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 | 83.0 | 104 | 83th | |
| GPQA Diamond | 73.2 | 194 | 68th | |
| SWE-bench Verified | 69.2 | 128 | 79th | |
| HumanEval | 85.5 | 105 | 83th | |
| MATH-500 | 81.2 | 185 | 69th | |
| AIME 2025 | 80.3 | 85 | 86th | |
| LiveCodeBench | 75.6 | 89 | 85th | |
| IFEval | 88.6 | 92 | 85th | |
| TruthfulQA | 82.3 | 123 | 80th | |
| HellaSwag | 89.9 | 88 | 85th | |
| MMMU | 75.1 | 162 | 73th | |
| Arena Elo | 1416.7 | 164 | 73th |
What GPT-5.2 Mini is good for
GPT-5.2 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 $13.34 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.
Strengths
- Large 200,000-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 $13.34 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| ERNIE 4.5 Pro | Baidu | 1000000 | $13.89 | 80.5 |
| Kimi K1.5 Instruct | Moonshot AI | 200000 | $5.15 | 80.5 |
| Sonar Pro Reasoning | Perplexity | 128000 | $13.94 | 80.5 |
| GLM-4.6 Instruct | Zhipu AI | 1000000 | $5.15 | 80.4 |
| GPT-5.2 Mini | OpenAI | 200000 | $13.34 | 80.4 |
| Qwen3 | Alibaba Cloud | 128000 | $5.04 | 80.3 |
FAQ
How much does GPT-5.2 Mini cost?
GPT-5.2 Mini is listed at $13.34 per million input tokens and $49.98 per million output tokens. Cached input is $1.98 per million tokens. A blended 3:1 input-to-output mix is about $22.50 per million tokens.
What is the context window of GPT-5.2 Mini?
GPT-5.2 Mini has a context window of 200,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is GPT-5.2 Mini open weights?
No. GPT-5.2 Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does GPT-5.2 Mini score on benchmarks?
GPT-5.2 Mini averages 80.4 across the scored benchmarks in this index, ranking #110 of 600 models. Its strongest relative result is Arena Elo at 1416.7.
What is GPT-5.2 Mini best for?
GPT-5.2 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 $13.34 per million input tokens, it sits in the mid-range of the index, and the 200,000-token context window is enough for large files and multi-file diffs.