Gemini 3 Pro Vision: pricing, context window and benchmarks
Gemini 3 Pro Vision is a frontier model from Google DeepMind. It offers a 200,000-token context window, costs $17.59 per million input tokens and $68.83 per million output tokens, and averages 85.5 across the index's benchmark suite.
Pricing
Gemini 3 Pro Vision costs $17.59 per million input tokens and $68.83 per million output tokens. A blended 3:1 input-to-output mix works out to about $30.40 per million tokens. Cached input is listed at $2.32 per million tokens.
| Item | Price | Notes |
|---|---|---|
| Input | $17.59 | per 1M tokens |
| Output | $68.83 | per 1M tokens |
| Cached input | $2.32 | per 1M tokens |
| Blended 3:1 | $30.40 | estimate per 1M tokens |
| 1M in + 1M out | $86.42 | 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 | 87.3 | 29 | 95th | |
| GPQA Diamond | 80.6 | 50 | 92th | |
| SWE-bench Verified | 76.5 | 25 | 96th | |
| HumanEval | 91.6 | 28 | 95th | |
| MATH-500 | 88.4 | 65 | 89th | |
| AIME 2025 | 87.3 | 18 | 97th | |
| LiveCodeBench | 79.2 | 53 | 91th | |
| IFEval | 90.4 | 64 | 89th | |
| TruthfulQA | 84.5 | 74 | 88th | |
| HellaSwag | 91.1 | 61 | 90th | |
| MMMU | 83.6 | 15 | 98th | |
| Arena Elo | 1458.1 | 57 | 91th |
What Gemini 3 Pro Vision is good for
Gemini 3 Pro Vision 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 $17.59 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 (85.5), placing it #41 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 $17.59 per million tokens.
- Cost can climb quickly on long outputs and high-volume traffic.
How it compares
| Model | Provider | Context | Input / 1M | Avg score |
|---|---|---|---|---|
| o3 Pro | OpenAI | 400000 | $17.89 | 85.8 |
| Claude Opus 4.5 Turbo | Anthropic | 2000000 | $19.57 | 85.7 |
| Gemini 3 Pro Vision | Google DeepMind | 200000 | $17.59 | 85.5 |
| Grok 4 Pro | xAI | 1000000 | $19.00 | 85.4 |
| o4 | OpenAI | 2000000 | $17.74 | 85.4 |
| o3 Reasoning | OpenAI | 200000 | $18.07 | 85.3 |
FAQ
How much does Gemini 3 Pro Vision cost?
Gemini 3 Pro Vision is listed at $17.59 per million input tokens and $68.83 per million output tokens. Cached input is $2.32 per million tokens. A blended 3:1 input-to-output mix is about $30.40 per million tokens.
What is the context window of Gemini 3 Pro Vision?
Gemini 3 Pro Vision has a context window of 200,000 tokens and can emit up to 128,000 output tokens per request in this index.
Is Gemini 3 Pro Vision open weights?
No. Gemini 3 Pro Vision is a proprietary model with a proprietary licence, so you cannot download the weights.
How does Gemini 3 Pro Vision score on benchmarks?
Gemini 3 Pro Vision averages 85.5 across the scored benchmarks in this index, ranking #41 of 600 models. Its strongest relative result is Arena Elo at 1458.1.
What is Gemini 3 Pro Vision best for?
Gemini 3 Pro Vision 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 $17.59 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.