Gemini 2.5 Pro
Google
google/gemini-2.5-pro
1M context, deep reasoning
Context Window
1.0M
1,000,000 tokens
Max Output
66K
65,536 tokens
About this model
Gemini 2.5 Pro is Google's flagship reasoning model with the industry's largest 1M token context window. It achieves top-tier performance in mathematical reasoning, code generation, and multimodal understanding.
Supports text, image, audio, and video input as a truly multimodal model. Excels on MATH and GPQA benchmarks. Context Caching is automatic, with cache hits saving 90% of input costs.
Highlights
1M token context
True multimodal
Top-tier math reasoning
90% cache discount
Best For
Ultra-long document analysisMath & science reasoningMultimodal tasksVideo understanding
2025-03-25MoE TransformerProprietary
Capabilities
ChatVisionReasoningCodepdftoolscache
Aliases
gemini-2.5-progeminigemini-latestgemini-proPricing (per 1M tokens)
| Pricing (per 1M tokens) | / 1M tokens |
|---|---|
| Input / 1M | $1.31 |
| Output / 1M | $10.50 |
| Cache Read | $0.13 |
Final prices shown
Quick Start
main.py
from openai import OpenAI client = OpenAI( base_url="https://api.chuizi.ai/v1", api_key="ck-your-key-here", ) response = client.chat.completions.create( model="google/gemini-2.5-pro", messages=[{"role": "user", "content": "Hello!"}], ) print(response.choices[0].message.content)