Gemini 3 Flash: pricing, context window and benchmarks
Gemini 3 Flash is a multimodal model from Google DeepMind. It offers a 128,000-token context window, costs $15.67 per million input tokens and $70.15 per million output tokens, and averages 83.6 across the index's benchmark suite.
Pricing
Gemini 3 Flash costs $15.67 per million input tokens and $70.15 per million output tokens. A blended 3:1 input-to-output mix works out to about $29.29 per million tokens. Cached input is listed at $1.28 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $15.67 | per 1M tokens |
| Output | $70.15 | per 1M tokens |
| Cached input | $1.28 | per 1M tokens |
| Blended 3:1 | $29.29 | estimate per 1M tokens |
| 1M in + 1M out | $85.82 | 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 | 83.7 | 87 | 86th | |
| GPQA Diamond | 80.3 | 52 | 91th | |
| SWE-bench Verified | 72.5 | 66 | 89th | |
| HumanEval | 86.2 | 100 | 83th | |
| MATH-500 | 89.0 | 59 | 90th | |
| AIME 2025 | 84.5 | 44 | 93th | |
| LiveCodeBench | 79.3 | 51 | 92th | |
| IFEval | 91.0 | 54 | 91th | |
| TruthfulQA | 84.8 | 66 | 89th | |
| HellaSwag | 89.8 | 91 | 85th | |
| MMMU | 78.2 | 92 | 85th | |
| Arena Elo | 1450.7 | 71 | 88th |
What Gemini 3 Flash is good for
Gemini 3 Flash 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 $15.67 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.
- 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 $15.67 per million tokens.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| Claude 3.7 Sonnet Max | Anthropic | 128000 | $16.88 | 83.7 |
| Claude 3.7 Sonnet Reasoning | Anthropic | 128000 | $16.30 | 83.7 |
| DeepSeek-V3.2 Instruct | DeepSeek | 128000 | $5.91 | 83.7 |
| Gemini 3 Flash Reasoning | Google DeepMind | 128000 | $17.05 | 83.7 |
| Gemini 2.5 Pro Pro | Google DeepMind | 400000 | $17.16 | 83.6 |
| Gemini 3 Flash | Google DeepMind | 128000 | $15.67 | 83.6 |
FAQ
How much does Gemini 3 Flash cost?
Gemini 3 Flash is listed at $15.67 per million input tokens and $70.15 per million output tokens. Cached input is $1.28 per million tokens. A blended 3:1 input-to-output mix is about $29.29 per million tokens.
What is the context window of Gemini 3 Flash?
Gemini 3 Flash has a context window of 128,000 tokens and can emit up to 65,536 output tokens per request in this index.
Is Gemini 3 Flash open weights?
No. Gemini 3 Flash is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Flash score on benchmarks?
Gemini 3 Flash averages 83.6 across the scored benchmarks in this index, ranking #69 of 600 models. Its strongest relative result is Arena Elo at 1450.7.
What is Gemini 3 Flash best for?
Gemini 3 Flash 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 $15.67 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.