Loading model…正在加载模型详情…
Chat with Google’s Gemini 2.5 Pro for coding and complex reasoning, online or by API.
- From $0.50 in / $4.00 out per 1M tokensSave up to 60%
- Gemini generateContent and OpenAI Chat Completions API
- Coding · Reasoning
What can I help you with?
Use it inGemini CLI
What is Gemini 2.5 Pro?
Gemini 2.5 Pro is a Google language model. Google describes it as an advanced thinking model for complex reasoning, code generation and long-context understanding.
Use the exact model ID gemini-2.5-pro with native generateContent or OpenAI-compatible Chat Completions. The API section shows both request formats.
Gemini 2.5 Pro belongs to Google’s Pro line, which emphasizes demanding reasoning and development work. The related models section links to later Pro versions so you can compare their capabilities and available rates.
What you can do
What Gemini 2.5 Pro is built for.
Code and technical problem solving
Describe a programming task, ask for an implementation or share code for explanation and review. Follow up to refine the approach.
Reasoning and knowledge work
Bring a question or source text into the conversation, ask for a structured analysis and explore assumptions with follow-up prompts.
Tool use in your application
The API supports function calling for applications that provide and execute their own tools. The chat box on this page handles text conversations.
This page’s chat box accepts text; attachments, search and thinking controls belong in API integrations and depend on the selected variant’s supported parameters.
Specs & variants
The variants you can call, with their options and prices.
| Variant | Model ID | Modes | Inputs | Output | Price |
|---|---|---|---|---|---|
| Gemini 2.5 Pro | gemini-2.5-pro | Chat and text generation | Gemini generateContent and OpenAI Chat Completions API | Thinking; Context window: Not stated on this page | $0.50 input / $4.00 output per 1M tokens |
Pricing
Priced per token. Input and output are billed separately.
| Usage | Official API | UniRoute | Save |
|---|---|---|---|
| Input | $1.25 | $0.50 | Save 60% |
| Output | $10.00 | $4.00 | Save 60% |
| Cache read | $0.125 | $0.05 | Save 60% |
Official price: ai.google.dev · 2026-11-07
Prices updated 2026-11-08.
Pay as you go from a single USD wallet balance. You see the quote before each request.
API
Call Gemini 2.5 Pro through Gemini generateContent and OpenAI Chat Completions API.
curl 'https://api.uniroute.app/v1beta/models/gemini-2.5-pro:generateContent' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "contents": [ { "role": "user", "parts": [ { "text": "Hello" } ] } ]}'curl 'https://api.uniroute.app/v1/chat/completions' \ -H 'Authorization: Bearer YOUR_API_KEY' \ -H 'Content-Type: application/json' \ -d '{ "model": "gemini-2.5-pro", "messages": [ { "role": "user", "content": "Hello" } ], "stream": false}'Parameters
| Name | In | Description |
|---|---|---|
model | Body | Model ID to run. |
messages | Body | The conversation as a list of role and content messages. |
stream | Body | Set to true to receive the response as a stream. |
models/<id> | Path | Model ID to run. |
contents | Body | Content items with role and text parts (Gemini generateContent). |
generationConfig | Body | Generation settings, including maxOutputTokens (Gemini generateContent). |
Guides
Benchmarks & ranking
Published scores next to the models they were compared with.
| Benchmark Area | Gemini 2.5 Pro | OpenAI o3-mini | OpenAI GPT-4.5 | Claude 3.7 Sonnet | Grok 3 Beta | |
|---|---|---|---|---|---|---|
| Reasoning & knowledge | Humanity’s Last Exam (no tools) | 18.80% | 14.00%* | 6.40% | 8.90% | – |
| Science | GPQA Diamond (single attempt, pass@1) | 84.00% | 79.70% | 71.40% | 78.20% | 80.20% |
| Mathematics | AIME 2025 (single attempt, pass@1) | 86.70% | 86.50% | – | 49.50% | 77.30% |
| Code generation | LiveCodeBench v5 (single attempt, pass@1) | 70.40% | 74.10% | – | – | 70.60% |
| Code editing | Aider Polyglot | 74.0% / 68.6% (whole / diff) | 60.4% (diff) | 44.9% (diff) | 64.9% (diff) | – |
| Visual reasoning | MMMU (single attempt, pass@1) | 81.70% | no MM support | 74.40% | 75.00% | 76.00% |
| Long context | MRCR (128k average) | 94.50% | 61.40% | 64.00% | – | – |
Figures published by Google from its own evaluations. Results depend on each benchmark’s configuration.
Use cases
Typical ways to put Gemini 2.5 Pro to work.
Coding assistance
Discuss a bug, compare implementation approaches or ask for a code review before applying changes to your project.
Document analysis
Paste source material and ask for a summary, a comparison or a list of open questions to investigate.
Application prototyping
Describe an interface or workflow, generate a first implementation and refine the result in conversation.
FAQ
Common questions about Gemini 2.5 Pro.
What is Gemini 2.5 Pro?
Gemini 2.5 Pro is a Google model for complex reasoning, code generation and document analysis. You can chat with it on this page or integrate it through the API.
How do I call it through the API?
Use the exact model ID gemini-2.5-pro with native generateContent or OpenAI-compatible Chat Completions. The API section shows both request formats.
Which version should I select?
This page exposes the model ID gemini-2.5-pro. Other Pro versions appear in Related models, where you can compare their descriptions and available pricing.
How much does Gemini 2.5 Pro cost?
From $0.50 input / $4.00 output per 1M tokens. Input and output are charged separately by token usage. The Pricing section lists the available rates and worked examples (prices updated 2026-11-08).
Can I use attachments and tools in this chat box?
No. This page provides a text conversation. API capabilities depend on the selected variant; check its listed parameters before adding attachments or tools to an integration.
Is there a free trial or free credits?
No. Requests are paid from your wallet balance. You can read this page and review the prices without paying, and you need an account with funds to send a message.
Related models
Other versions, models from the same provider and alternatives.
