Gemini 1.5 Pro: Pricing, Context, and Benchmarks
Gemini 1.5 Pro is Google's Gemini 1 model released on 2024-02-15. It runs on a 2.0M-token context window, priced at $1.25/M input and $5.00/M output. First 1M+ context window model. Still actively used; pricing kept low to drive migration to 2.5.
Specifications
| Provider | |
|---|---|
| Family | Gemini 1 |
| Released | 2024-02-15 |
| Status | active |
| Context window | 2.0M tokens |
| Max output | 8K tokens |
| Modalities | text image audio video |
| Capabilities | function calling json mode vision streaming audio video |
| Tokenizer | gemini |
| API endpoint | https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro:generateContent |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
What this model is good for
Based on benchmark scores and capability fit, Gemini 1.5 Pro ranks well for:
- Long Context Summarization — rank #2. Same 2M context, older model, cheaper.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0063 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.000750 | $0.75 | $750 |
| Standard chat | 1K / 500 | $0.003750 | $3.75 | $3,750 |
| RAG with retrieval | 4K / 500 | $0.007500 | $7.50 | $7,500 |
| Long doc summary | 20K / 1K | $0.030000 | $30.00 | $30,000 |
| Long context (100K input) | 100K / 2K | $0.132500 | $132.50 | $132,500 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other Google models
Common comparisons
- Gemini 1.5 Pro vs GPT-5 Side-by-side specs, pricing, and benchmarks
- Gemini 1.5 Pro vs o3-mini Side-by-side specs, pricing, and benchmarks
- Gemini 1.5 Pro vs Claude Haiku 4.5 Side-by-side specs, pricing, and benchmarks
- Gemini 1.5 Pro vs Llama 3.3 70B Side-by-side specs, pricing, and benchmarks
API setup
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-1.5-pro:generateContent \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gemini-1-5-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.