Google: Gemini 2.5 Pro
Overview
Model Name: Google: Gemini 2.5 Pro
Creator: Google
Release Date: June 17, 2025
Identifier: google/gemini-2.5-pro
Description: State-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks
Key Capabilities
- Input Modalities: Text, image, file, audio, video
- Output Modalities: Text only
- Context Window: 1,048,576 tokens
- Maximum Completion Tokens: 65,536
- Special Features: Reasoning support (mandatory)
Pricing
Base Rates
| Component | Cost |
|---|---|
| Input | $1.25 per 1M tokens |
| Output | $10.00 per 1M tokens |
Volume Discounts (200,000+ tokens)
| Component | Cost |
|---|---|
| Input | $2.50 per 1M tokens |
| Output | $15.00 per 1M tokens |
Additional Pricing
| Service | Cost |
|---|---|
| Image processing | $0.516 per image |
| Input cache read | $0.125 per 1M tokens |
| Input cache write | $1.625 per 1M tokens |
Performance
- Benchmark Achievement: Top-tier performance on multiple benchmarks
- LMArena Ranking: First-place positioning
- Strengths: Superior human-preference alignment and complex problem-solving abilities
- Specialization: Advanced reasoning, coding, mathematics, and scientific tasks
Detailed Analysis
Google Gemini 2.5 Pro Preview 05-06 (May 2025 Enhanced)
Daily Request Volume: Consistently exceeds 1.1 million calls
Token Consumption: Significant volume spanning:
- Reasoning operations
- Cached content
- Media processing across multiple input formats
Providers
| Property | Details |
|---|---|
| Provider | Google Vertex (Global) |
| Adapter | GoogleVertexGeminiAdapter |
| Rate Limits | 300 requests per minute |
| Status Page | https://status.cloud.google.com |
Parameters
Supported Configuration Options:
- Response formatting
- Structured outputs
- Tool use and selection
- Temperature control
- Top-p sampling
- Seed specification
- Stop sequences
- Reasoning configuration