Gemini 2.5 Pro Mini: pricing, context window and benchmarks
Gemini 2.5 Pro Mini is a multimodal model from Google DeepMind. It offers a 128,000-token context window, costs $10.07 per million input tokens and $53.47 per million output tokens, and averages 74.2 across the index's benchmark suite.
Pricing
Gemini 2.5 Pro Mini costs $10.07 per million input tokens and $53.47 per million output tokens. A blended 3:1 input-to-output mix works out to about $20.92 per million tokens. Cached input is listed at $1.16 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $10.07 | per 1M tokens |
| Output | $53.47 | per 1M tokens |
| Cached input | $1.16 | per 1M tokens |
| Blended 3:1 | $20.92 | estimate per 1M tokens |
| 1M in + 1M out | $63.54 | 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 | 206 | 66th | |
| GPQA Diamond | 69.9 | 266 | 56th | |
| SWE-bench Verified | 63.6 | 242 | 60th | |
| HumanEval | 79.0 | 265 | 56th | |
| MATH-500 | 76.0 | 298 | 50th | |
| AIME 2025 | 68.2 | 292 | 51th | |
| LiveCodeBench | 65.4 | 284 | 53th | |
| IFEval | 81.5 | 287 | 52th | |
| TruthfulQA | 78.4 | 239 | 60th | |
| HellaSwag | 83.3 | 312 | 48th | |
| MMMU | 71.4 | 263 | 56th | |
| Arena Elo | 1399.4 | 209 | 65th |
What Gemini 2.5 Pro Mini is good for
Gemini 2.5 Pro Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $10.07 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.
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.
Trade-offs
- Proprietary licence: you cannot download the weights or self-host the model.
- Premium input pricing at $10.07 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| GPT-4.1 Mini | OpenAI | 128000 | $10.43 | 74.3 |
| Nova Lite Reasoning | Amazon | 32768 | $9.92 | 74.3 |
| Gemini 2.5 Pro Mini | Google DeepMind | 128000 | $10.07 | 74.2 |
| Llama 3 Novita Chat | Novita AI | 65536 | $3.50 | 74.2 |
| Gemma 3 Instruct | Google DeepMind | 128000 | $3.72 | 74.1 |
| Reka Flash | Reka AI | 128000 | $9.95 | 74.1 |
FAQ
How much does Gemini 2.5 Pro Mini cost?
Gemini 2.5 Pro Mini is listed at $10.07 per million input tokens and $53.47 per million output tokens. Cached input is $1.16 per million tokens. A blended 3:1 input-to-output mix is about $20.92 per million tokens.
What is the context window of Gemini 2.5 Pro Mini?
Gemini 2.5 Pro Mini has a context window of 128,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Gemini 2.5 Pro Mini open weights?
No. Gemini 2.5 Pro Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 2.5 Pro Mini score on benchmarks?
Gemini 2.5 Pro Mini averages 74.2 across the scored benchmarks in this index, ranking #270 of 600 models. Its strongest relative result is Arena Elo at 1399.4.
What is Gemini 2.5 Pro Mini best for?
Gemini 2.5 Pro Mini is a general-purpose model in the index. It handles text generation, summarization and question answering, and it can be a sensible default when you need a balance of quality, price and context. At $10.07 per million input tokens with a 128,000-token window, check its benchmark profile against the specific task before committing.