Gemini 3 Pro Preview
gemini-3-pro-previewCompare gemini-3-pro-preview API pricing, supported endpoints, capabilities and access options on Modelsell.
- Starting price
- Input / Output · 1M
- Context
- 1M
- Maximum input window
- Max output
- 65.5K
- Maximum tokens per response
- Modalities
- →
- Released
- Nov 2025
Pricing by Supplier
Capabilities / Supported modalities
Provider & data privacy
SentencePiece (Gemini)Performance
Benchmarks
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·Gemini 3 Pro Preview
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
About Gemini 3 Pro Preview
把不同形式的资料放在一起分析
Gemini 3 Pro Preview 面向复杂推理和多模态理解，可接收文字、图片、视频、音频及 PDF，输出文字结果。它适合将分散资料整理成可用结论，例如结合产品演示录像、需求讨论音频和技术文档，找出功能关系、实现约束与仍待确认的问题。
百万级输入窗口有助于分析长文档、代码与较多素材。资料最好有明确分工：文档提供规则，录屏展示过程，截图补充细节，音频保留讨论背景。要求结论对应页码、时间点或具体材料，能够更容易检查模型是否混淆了不同来源。
从理解到可执行结果
模型支持思考、结构化输出与函数调用，可以将分析整理为固定字段，或在应用提供工具后推进多步骤工作。它也支持代码执行、文件检索、搜索依据和 URL 上下文等能力，需要在请求与应用中配置相应工具。实际执行结果应交回模型，供后续判断使用。
复杂任务可先列关键约束，再提出方案，最后检查反例与遗漏。例如根据演示和接口文档规划开发时，区分已经展示的行为、文档规定的行为与推测的行为；对看不清的画面或未明确的要求提出待确认项。
Google 官方已于 2026 年 3 月 9 日停止该预览服务，新任务可选择 Gemini 3.1 Pro Preview 等受支持型号，并重新检查现有工具与素材流程。
Use cases and prompting
分析产品演示与规格文档
“结合演示视频、需求讨论音频和 PDF 规格，整理待开发功能。每项注明对应页码或时间点，区分已明确要求与推测。检查流程中的异常状态，提出最小实现顺序及验收步骤，不替缺失需求编造答案。”
多种素材怎样避免混淆？
为每份材料命名，说明录制时间、版本和用途，并要求回答标明依据。
有音频输入就能生成语音吗？
本型号用文字输出分析结果。音频属于理解素材，制作语音成品需要另接语音合成服务。
API access
API documentation
Code samples
/v1beta/models/gemini-3-pro-preview:generateContent| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| Google AI Studio | Unlimited | Unlimited | Unlimited |
| Google Vertex | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about gemini-3-pro-preview
What is gemini-3-pro-preview?
Compare gemini-3-pro-preview API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call gemini-3-pro-preview?
Create an API key with access to gemini-3-pro-preview, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
How is gemini-3-pro-preview priced?
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
What is the context window of gemini-3-pro-preview?
The model catalog lists a context window of 1048576 tokens. Check the selected endpoint for request limits.
What is the maximum output of gemini-3-pro-preview?
The model catalog lists a maximum output of 65536 tokens. Your request settings may set a lower limit.
How should I evaluate gemini-3-pro-preview for my project?
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.