Gemini 3.1 Pro Preview
gemini-3.1-pro-previewCompare gemini-3.1-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
- Feb 2026
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 3.1 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 3.1 Pro Preview
将多种材料放到同一个问题里
Gemini 3.1 Pro Preview 适合同时涉及复杂推理与多种输入的工作。你可以把 PDF 方案、演示视频、会议录音和代码说明一起提供，让它分析同一项目中的需求、操作过程与实现约束。它输出文字，适合形成技术报告、代码、摘要或结构化记录。
在软件工程中，它可参与代码理解、故障分析和实现计划，也适合需要多次工具调用的智能体任务。比如先读接口文档，再检查代码，最后根据测试结果修订方案。调用端提供工具后，模型可以选择何时查询、计算或调用业务函数；每一步的结果都应作为后续分析的依据。
音视频理解让它能回答文字资料之外的问题：从产品演示中整理操作步骤、从培训录音中提取讨论结论，或将视频里的界面变化与需求文档对照。请求中注明关注的时间段、人物或页面，会更容易得到针对性结果。它不是语音或视频生成模型，也不通过 Live API 提供实时对话。
长上下文适合阅读大型资料包，结构化输出方便将内容转换为系统字段。接入搜索 grounding、URL 上下文或代码执行工具后，还可以补充时效信息、阅读指定网页和核算数据；需要在请求中实际启用对应能力。对于图片中的表格和 PDF 扫描件，要求保留页码与原文摘录有助于复核。
如何使用更顺手
能分析整段演示视频吗？ 可以提交支持的视频输入，并说明要检查的行为，要求用时间位置标记发现。
适合长期固定流程吗？ Preview 版本适合验证能力与构建应用，上线前应使用代表性样本检查格式、工具调用和任务完成率，并关注版本更新。
Use cases and prompting
让不同输入互相验证
为材料命名，并指定最终需要解决的问题。
材料 A 是产品操作视频，材料 B 是功能需求 PDF。
检查视频中的登录、筛选和导出流程是否符合需求。
按功能列出：需求页码、视频时间点、实际表现、差异与复现步骤。
最后生成验收清单；视频看不到的功能标为“未展示”，不要判断为已完成。
代码与工具任务写清可调用工具、完成标准和错误处理方式。分析音频时可以要求区分原话、摘要和推断；使用搜索工具时指定日期范围和证据要求，让结论与引用的材料保持对应。
API access
API documentation
Code samples
/v1beta/models/gemini-3.1-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 |
| default | Unlimited | Unlimited | Unlimited |
| Gemini Cli | Unlimited | Unlimited | Unlimited |
No restriction
Frequently asked questions about gemini-3.1-pro-preview
What is gemini-3.1-pro-preview?
Compare gemini-3.1-pro-preview API pricing, supported endpoints, capabilities and access options on Modelsell.
How do I call gemini-3.1-pro-preview?
Create an API key with access to gemini-3.1-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-3.1-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-3.1-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-3.1-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-3.1-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.