Gemini 2.5 Pro: Pricing, Context, and Benchmarks
Gemini 2.5 Pro is Google's Gemini 2 model released on 2025-03-25. It runs on a 2.0M-token context window, priced at $1.25/M input and $10.00/M output. Google's frontier reasoning model. 2M-token context window and built-in thinking mode.
Specifications
| Provider | |
|---|---|
| Family | Gemini 2 |
| Released | 2025-03-25 |
| Status | active |
| Context window | 2.0M tokens |
| Max output | 66K tokens |
| Modalities | text image audio video |
| Capabilities | function calling json mode vision streaming audio video thinking |
| Tokenizer | gemini |
| API endpoint | https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
Benchmark scores
| Benchmark | Category | Score | Measured | Source |
|---|---|---|---|---|
| AIME 2025 | math | 86.7 | 2025-03-25 | ↗ |
| MMLU-Pro | general | 86.4 | 2025-03-25 | ↗ |
| GPQA Diamond | reasoning | 84.0 | 2025-03-25 | ↗ |
| SWE-bench Verified | coding | 63.8 | 2025-03-25 | ↗ |
Scores reflect single measurements on the date shown. Reproducibility varies; consult the linked source for methodology. Use the comparison tool for side-by-side analysis.
What this model is good for
Based on benchmark scores and capability fit, Gemini 2.5 Pro ranks well for:
- Long Context Summarization — rank #1. 2M-token context window. Cheaper per token than Claude on long documents.
- Vision / Image Analysis — rank #2. Native video understanding gives Gemini the edge for video tasks.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0113 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.001250 | $1.25 | $1,250 |
| Standard chat | 1K / 500 | $0.006250 | $6.25 | $6,250 |
| RAG with retrieval | 4K / 500 | $0.010000 | $10.00 | $10,000 |
| Long doc summary | 20K / 1K | $0.035000 | $35.00 | $35,000 |
| Long context (100K input) | 100K / 2K | $0.140000 | $140.00 | $140,000 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other Google models
Common comparisons
- Gemini 2.5 Pro vs GPT-5 Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Pro vs o3-mini Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Pro vs Claude Haiku 4.5 Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Pro vs Llama 3.3 70B Side-by-side specs, pricing, and benchmarks
API setup
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gemini-2-5-pro", "messages": [{"role": "user", "content": "Hello"}]}'See the official documentation for the full request/response schema. For pre-flight token counting before paying, use the appropriate token counter.