Gemini 3 Flash Turbo: pricing, context window and benchmarks
Gemini 3 Flash Turbo is a frontier model from Google DeepMind. It offers a 200,000-token context window, costs $17.07 per million input tokens and $69.05 per million output tokens, and averages 84.1 across the index's benchmark suite.
Pricing
Gemini 3 Flash Turbo costs $17.07 per million input tokens and $69.05 per million output tokens. A blended 3:1 input-to-output mix works out to about $30.06 per million tokens. Cached input is listed at $2.45 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.07 | per 1M tokens |
| Output | $69.05 | per 1M tokens |
| Cached input | $2.45 | per 1M tokens |
| Blended 3:1 | $30.06 | estimate per 1M tokens |
| 1M in + 1M out | $86.12 | 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 | 87.9 | 18 | 97th | |
| GPQA Diamond | 77.5 | 96 | 84th | |
| SWE-bench Verified | 72.5 | 68 | 89th | |
| HumanEval | 90.6 | 37 | 94th | |
| MATH-500 | 87.6 | 70 | 88th | |
| AIME 2025 | 81.3 | 69 | 89th | |
| LiveCodeBench | 78.5 | 60 | 90th | |
| IFEval | 88.9 | 85 | 86th | |
| TruthfulQA | 87.4 | 29 | 95th | |
| HellaSwag | 89.5 | 99 | 84th | |
| MMMU | 83.0 | 23 | 96th | |
| Arena Elo | 1473.4 | 27 | 96th |
What Gemini 3 Flash Turbo is good for
Gemini 3 Flash 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 $17.07 per million input tokens and a 200,000-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 (84.1), placing it #56 of 600.
- Large 200,000-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 $17.07 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Gemini 3 Flash Turbo | Google DeepMind | 200000 | $17.07 | 84.1 |
| DeepSeek-V3.2 | DeepSeek | 1000000 | $5.88 | 84.0 |
| Gemini 2.5 Pro Turbo | Google DeepMind | 1000000 | $16.32 | 83.9 |
| Claude Haiku 4.5 Max | Anthropic | 200000 | $15.98 | 83.8 |
| GPT-4.1 Reasoning | OpenAI | 1000000 | $16.97 | 83.8 |
| Grok 3 Pro | xAI | 400000 | $16.61 | 83.8 |
FAQ
How much does Gemini 3 Flash Turbo cost?
Gemini 3 Flash Turbo is listed at $17.07 per million input tokens and $69.05 per million output tokens. Cached input is $2.45 per million tokens. A blended 3:1 input-to-output mix is about $30.06 per million tokens.
What is the context window of Gemini 3 Flash Turbo?
Gemini 3 Flash Turbo has a context window of 200,000 tokens and can emit up to 16,384 output tokens per request in this index.
Is Gemini 3 Flash Turbo open weights?
No. Gemini 3 Flash Turbo is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Flash Turbo score on benchmarks?
Gemini 3 Flash Turbo averages 84.1 across the scored benchmarks in this index, ranking #56 of 600 models. Its strongest relative result is Arena Elo at 1473.4.
What is Gemini 3 Flash Turbo best for?
Gemini 3 Flash 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 $17.07 per million input tokens and a 200,000-token context window, it is a premium option, so reserve it for tasks where a cheaper model measurably fails.