Gemini

Gemini 2.5 Pro

GoogleToken-based
Alias:gemini-2.5-pro
Create API Key

Compare gemini-2.5-pro API pricing, supported endpoints, capabilities and access options on voguesly.

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
→
Knowledge cutoff
Jan 2025
Released
Jun 2025

Pricing by Supplier

Google AI Studio
-70%
谷歌官方接口
Input/ 1M tokens
$0.375$1.25
Output/ 1M tokens
$3$10
Cache Read/ 1M tokens
$0.0375$0.125
Google Vertex
-65%
谷歌官方接口
Input/ 1M tokens
$0.4375$1.25
Output/ 1M tokens
$3.5$10
Cache Read/ 1M tokens
$0.04375$0.125

Capabilities / Supported modalities

Prompt cachingCode interpreterFunction callingToolsWeb searchStructured outputReasoningVision
Input
Output

Provider & data privacy

Provider
GoogleDocs
Tokenizer
SentencePiece (Gemini)
License
Proprietary (commercial)Proprietary
Data retention84 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 2.5 Pro

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 2.5 Pro

适合需要推导与交叉检查的问题

Gemini 2.5 Pro 是面向复杂问题的思考模型,适合代码分析、数学推导、科学技术问答,以及大型资料集合的理解。它能够将文档中的条件、图表里的信息与已有代码联系起来,给出分析步骤、实现建议或专业解释。

对于研发工作,可以让它阅读一组模块和接口文档,说明数据如何流动、哪些假设会在边界条件下失效,再设计修复与测试。对于学习和研究,可以要求它列清变量、假设和推导过程,比较不同方法的适用条件,并检查结论是否满足题目要求。

它支持文字、图片、音频、视频和 PDF 输入,输出文字。因此既能解释教材图示,也能分析讲座录音和实验演示视频。请求中最好指定页码、时间范围或关注对象,并区分观察到的现象与进一步推论。大上下文方便关联长资料,但精确问题和材料标记仍是获得有用答案的关键。

函数调用、结构化输出和代码执行等能力,使它可以参与数据分析与应用流程。需要计算时,让它通过实际工具验证数值;需要新信息时,启用搜索 grounding 或指定网页上下文,再依据获取到的材料作答。图像、音频和视频在这里用于理解,结果以文本形式交付。

使用前考虑

数学答案怎样更容易核验? 要求写清前提、单位和关键步骤,最后用代入或独立计算检查结果。

适合分析较大的代码库吗? 可以围绕一个功能或故障提供相关文件,先建立模块关系,再逐步深入;保留可运行的测试作为判断依据。

Use cases and prompting

给出问题条件与验证要求

复杂推理任务应包含完整条件,说明希望看到的分析深度。

根据这份实验说明和测量表,分析传感器读数为何随温度漂移。
先列变量、单位和可能机制,再检查数据是否支持这些解释。
给出可验证的校正方案与下一轮实验设计;所有计算说明公式,缺少的参数单独列出。
不要把相关性直接写成因果关系。

代码任务附上相关实现和输入样本,要求测试边界情况。分析 PDF 或视频时,返回页码或时间位置;用工具计算后检查量纲、数据范围和结果合理性,再写最终结论。

API access

API documentation

Code samples

RequestPOST/v1beta/models/gemini-2.5-pro: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

No restriction

Frequently asked questions about gemini-2.5-pro

What is gemini-2.5-pro?

Compare gemini-2.5-pro API pricing, supported endpoints, capabilities and access options on voguesly.

How do I call gemini-2.5-pro?

Create an API key with access to gemini-2.5-pro, 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-2.5-pro 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-2.5-pro?

The model catalog lists a context window of 1048576 tokens. Check the selected endpoint for request limits.

What is the maximum output of gemini-2.5-pro?

The model catalog lists a maximum output of 65536 tokens. Your request settings may set a lower limit.

How should I evaluate gemini-2.5-pro for my project?

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