Gemini 3 Pro Turbo: pricing, context window and benchmarks
Gemini 3 Pro Turbo is a frontier model from Google DeepMind. It offers a 400,000-token context window, costs $19.62 per million input tokens and $89.91 per million output tokens, and averages 86.4 across the index's benchmark suite.
Pricing
Gemini 3 Pro Turbo costs $19.62 per million input tokens and $89.91 per million output tokens. A blended 3:1 input-to-output mix works out to about $37.19 per million tokens. Cached input is listed at $2.39 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $19.62 | per 1M tokens |
| Output | $89.91 | per 1M tokens |
| Cached input | $2.39 | per 1M tokens |
| Blended 3:1 | $37.19 | estimate per 1M tokens |
| 1M in + 1M out | $109.53 | 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 | 85.6 | 57 | 91th | |
| GPQA Diamond | 81.0 | 43 | 93th | |
| SWE-bench Verified | 77.4 | 20 | 97th | |
| HumanEval | 90.3 | 41 | 93th | |
| MATH-500 | 92.4 | 16 | 97th | |
| AIME 2025 | 82.8 | 57 | 91th | |
| LiveCodeBench | 82.7 | 17 | 97th | |
| IFEval | 93.4 | 18 | 97th | |
| TruthfulQA | 87.8 | 23 | 96th | |
| HellaSwag | 94.6 | 8 | 99th | |
| MMMU | 82.7 | 26 | 96th | |
| Arena Elo | 1494.9 | 6 | 99th |
What Gemini 3 Pro Turbo is good for
Gemini 3 Pro Turbo sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $19.62 per million input tokens and a 400,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.
Strengths
- Top-tier average benchmark score (86.4), placing it #27 of 600.
- Large 400,000-token context window for long documents and agent traces.
- Accepts more than text, including image input where the provider supports it.
- Reasoning-oriented profile, useful for multi-step problems and structured analysis.
- 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 $19.62 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Grok 4 Max | xAI | 2000000 | $19.70 | 86.6 |
| o4 Turbo | OpenAI | 2000000 | $19.34 | 86.6 |
| Grok 4 | xAI | 200000 | $17.90 | 86.5 |
| Gemini 3 Pro Turbo | Google DeepMind | 400000 | $19.62 | 86.4 |
| Qwen3-Max Pro | Alibaba Cloud | 400000 | $18.87 | 86.2 |
| o4 Max | OpenAI | 2000000 | $19.51 | 86.2 |
FAQ
How much does Gemini 3 Pro Turbo cost?
Gemini 3 Pro Turbo is listed at $19.62 per million input tokens and $89.91 per million output tokens. Cached input is $2.39 per million tokens. A blended 3:1 input-to-output mix is about $37.19 per million tokens.
What is the context window of Gemini 3 Pro Turbo?
Gemini 3 Pro Turbo has a context window of 400,000 tokens and can emit up to 16,384 output tokens per request in this index.
Is Gemini 3 Pro Turbo open weights?
No. Gemini 3 Pro Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Pro Turbo score on benchmarks?
Gemini 3 Pro Turbo averages 86.4 across the scored benchmarks in this index, ranking #27 of 600 models. Its strongest relative result is Arena Elo at 1494.9.
What is Gemini 3 Pro Turbo best for?
Gemini 3 Pro Turbo sits in the frontier tier of the index. It is aimed at work where answer quality matters more than unit cost: hard reasoning, multi-step coding, document analysis and multimodal inputs. At $19.62 per million input tokens and a 400,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.