Gemini

Gemini 3.1 Pro Preview Customtools

GoogleToken-based
Alias:gemini-3.1-pro-preview-customtools
Create API Key

Compare gemini-3.1-pro-preview-customtools API pricing, supported endpoints, capabilities and access options on Modelsell.

textimageaudiovideofilecachingcode_interpreterfunction_callingtoolsweb_searchstructured_outputjson_modereasoningvisioncontext:1048576
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

Google AI Studio
-50%
谷歌官方接口
Input$2$1/ 1M
Output$12$6/ 1M
Cache Read$0.2$0.1/ 1M
Google Vertex
-30%
谷歌官方接口
Input$2$1.4/ 1M
Output$12$8.4/ 1M
Cache Read$0.2$0.14/ 1M

Capabilities / Supported modalities

Prompt cachingCode interpreterFunction callingToolsWeb searchStructured outputReasoningVision
Input
Output

Provider & data privacy

Provider
GoogleDocs
Tokenizer
SentencePiece (Gemini)
License
Proprietary (commercial)Proprietary
Data retention17 daysNot used for upstream training by default

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 Customtools

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 Customtools

让智能体优先使用你的工具

Gemini 3.1 Pro Preview Customtools 适合已经建立工具体系的开发团队。它在选择操作时更偏向你定义的工具,例如读取文件、搜索代码、查询内部系统,再结合 Bash 完成需要多步推进的任务。对于拥有专用工具和权限边界的编程助手,这种选择倾向能更好地衔接现有工作流。

你可以让它先调用代码检索找到实现,再读取相关文件、执行测试,最后依据反馈修改方案。工具名称、参数说明和返回结构应足够明确,尤其要区分“查找位置”“读取内容”和“执行修改”,让模型知道每种工具解决什么问题。工具输出包含文件路径、错误信息和可用状态时,也更便于它决定下一步。

它保留 Gemini 3.1 Pro Preview 的复杂推理与多模态理解能力,可以分析文本、图片、音频、视频和 PDF,并输出文字或结构化结果。例如,让开发智能体结合需求 PDF 与页面录像定位问题,再使用项目专用工具查询组件实现。较大的上下文窗口有利于保留跨文件材料和任务进度。

这个变体的价值主要体现在自定义工具与 Bash 协作场景。若应用主要是普通问答、写作或摘要,没有相应工具,标准 Pro 版本通常更适合作为对照进行评估。工具优先倾向也需要结合实际任务验证,建议检查调用是否必要、参数是否正确,以及失败后能否恢复。

接入时常见问题

会自动获得文件和终端权限吗? 需要应用提供工具与执行环境,并决定可读写范围;模型选择工具不会替应用完成权限配置。

怎样减少错误调用? 为相似工具写清区别,规定错误返回格式,并要求修改后运行相应验证。

Use cases and prompting

先说明工具职责与执行顺序

给智能体一个真实目标,并把工具约束写进任务。

修复用户修改邮箱后通知仍发往旧地址的问题。
先用 search_code 查找邮箱更新和通知收件人逻辑,用 view_file 阅读相关实现,再运行项目测试。
只修改账户与通知相关代码;不要调整数据库连接或生产配置。
若工具返回无权限或文件缺失,记录阻塞位置,不猜测执行成功。
完成后列出修改文件、根因和测试结果。

工具定义中明确参数类型、读取与写入的区别、失败返回方式。运行前准备代表性任务,对比标准 Pro 与 Customtools 的工具选择和完成情况,再确定适合的工作流。

API access

API documentation

Code samples

RequestPOST/v1beta/models/gemini-3.1-pro-preview-customtools:generateContent
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

Generation parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

SupplierRPMTPMRPD
Google AI StudioUnlimitedUnlimitedUnlimited
Google VertexUnlimitedUnlimitedUnlimited
defaultUnlimitedUnlimitedUnlimited

No restriction

Frequently asked questions about gemini-3.1-pro-preview-customtools

What is gemini-3.1-pro-preview-customtools?

Compare gemini-3.1-pro-preview-customtools API pricing, supported endpoints, capabilities and access options on Modelsell.

How do I call gemini-3.1-pro-preview-customtools?

Create an API key with access to gemini-3.1-pro-preview-customtools, 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-customtools 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-customtools?

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-customtools?

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-customtools for my project?

Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.