Gemini 2.5 Pro

by Google

Gemini 2.5 Pro is Google's high-end Gemini 2.5 thinking model, built for complex reasoning across mathematics, STEM, and software development. With a 1M-token context window and an extended reasoning mode, it works through intricate problems step by step, a fit for scientific research, advanced coding, and multi-step agentic workflows. The model accepts multimodal inputs including text, images, audio, video, and PDFs, so it can analyze entire codebases, research papers, and heterogeneous datasets in a single request. It supports function calling, structured outputs, code execution, and grounding with both Google Search and Google Maps. Compare it to Gemini 2.5 Flash for price-sensitive general tasks, or to Gemini 3.1 Pro for the latest generation with improved agentic capability and reasoning performance. Gemini 2.5 Pro remains strong for reasoning-heavy applications where accuracy matters most.

Key info

Input
Output
Features
Context window
1M
Max output
66K
Input price
$1.25 /1M
Output price
$10.00 /1M
  • EU residency available
  • Zero data retention via Enterprise
  • No training by default
  • GDPR DPA available

Available routes

Gemini 2.5 Pro runs on 2 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance β€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
Google CloudEUEnterpriseNo$1.25$10.00
Google CloudEUEnterpriseNo$1.25$10.00

Training posture across routes: No training on prompts by default.

Data handling per route

Each route hosting Gemini 2.5 Pro has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.

Google Cloud β€” European UnionπŸ‡ͺπŸ‡Ί

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Google Cloud β€” European UnionπŸ‡ͺπŸ‡Ί

Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.

Zero data retention
Available via Opper Enterprise contract.
Training
No training on customer data.
Logging
Abuse monitoring
Third-party access
None disclosed
GDPR DPA
DPA available
Transfer mechanism
Not applicable β€” data stays in EU

Benchmarks

Independent benchmark scores β€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#125 of 531 LLMs
TierEfficient
Output speed131 tok/s
First token18.90s
Intelligence Index27.0
Coding Index32.0
Math Index87.7
Reasoning & knowledge
MMLU-Pro
86%
GPQA Diamond
84%
Humanity's Last Exam
21%
Long-context reasoning
66%
Coding
LiveCodeBench
80%
SciCode
43%
Agentic & tool use
Terminal-Bench Hard
27%
τ²-Bench Telecom
54%
Math & instruction following
AIME 2025
88%
IFBench
49%

Get started

Call Gemini 2.5 Pro through the Opper gateway with one API key. Let your coding agent set it up, or call it directly β€” Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into your coding agent β€” Claude Code, Cursor, Codex, and more β€” and it'll wire up Opper for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.OPPER_API_KEY,
baseURL: "https://api.opper.ai/v3/compat",
});
const completion = await client.chat.completions.create({
model: "vertexai/gemini-2.5-pro",
messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Compare Gemini 2.5 Pro with…

Side-by-side on privacy, EU hosting, pricing, and benchmarks.

Other models from Google

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
Gemini 2.5 Pro by Google β€” pricing, benchmarks, EU hosting | Opper AI