Gemini 3 Pro Mini: pricing, context window and benchmarks
Gemini 3 Pro Mini is a multimodal model from Google DeepMind. It offers a 128,000-token context window, costs $12.27 per million input tokens and $57.81 per million output tokens, and averages 78.1 across the index's benchmark suite.
Pricing
Gemini 3 Pro Mini costs $12.27 per million input tokens and $57.81 per million output tokens. A blended 3:1 input-to-output mix works out to about $23.66 per million tokens. Cached input is listed at $1.31 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $12.27 | per 1M tokens |
| Output | $57.81 | per 1M tokens |
| Cached input | $1.31 | per 1M tokens |
| Blended 3:1 | $23.66 | estimate per 1M tokens |
| 1M in + 1M out | $70.08 | 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 | 79.4 | 199 | 67th | |
| GPQA Diamond | 72.1 | 217 | 64th | |
| SWE-bench Verified | 68.0 | 146 | 76th | |
| HumanEval | 83.5 | 143 | 76th | |
| MATH-500 | 81.3 | 182 | 70th | |
| AIME 2025 | 77.5 | 121 | 80th | |
| LiveCodeBench | 70.8 | 175 | 71th | |
| IFEval | 86.2 | 149 | 75th | |
| TruthfulQA | 80.0 | 177 | 71th | |
| HellaSwag | 85.8 | 222 | 63th | |
| MMMU | 74.5 | 169 | 72th | |
| Arena Elo | 1419.9 | 149 | 75th |
What Gemini 3 Pro Mini is good for
Gemini 3 Pro 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 $12.27 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 $12.27 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| DeepSeek-Coder | DeepSeek | 32768 | $4.55 | 78.1 |
| Gemini 3 Pro Mini | Google DeepMind | 128000 | $12.27 | 78.1 |
| Hunyuan-Large Chat | Tencent | 200000 | $4.35 | 78.1 |
| Qwen3-Coder Instruct | Alibaba Cloud | 128000 | $4.66 | 78.1 |
| ERNIE 4.0 Turbo | Baidu | 65536 | $12.00 | 78.0 |
| Llama 4 Scout Chat | Meta AI | 32768 | $4.66 | 78.0 |
FAQ
How much does Gemini 3 Pro Mini cost?
Gemini 3 Pro Mini is listed at $12.27 per million input tokens and $57.81 per million output tokens. Cached input is $1.31 per million tokens. A blended 3:1 input-to-output mix is about $23.66 per million tokens.
What is the context window of Gemini 3 Pro Mini?
Gemini 3 Pro Mini has a context window of 128,000 tokens and can emit up to 4,096 output tokens per request in this index.
Is Gemini 3 Pro Mini open weights?
No. Gemini 3 Pro Mini is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Pro Mini score on benchmarks?
Gemini 3 Pro Mini averages 78.1 across the scored benchmarks in this index, ranking #170 of 600 models. Its strongest relative result is Arena Elo at 1419.9.
What is Gemini 3 Pro Mini best for?
Gemini 3 Pro 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 $12.27 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.