Gemini 2.5 Flash: Pricing, Context, and Benchmarks
Gemini 2.5 Flash is Google's Gemini 2 model released on 2025-04-09. It runs on a 1.0M-token context window, priced at $0.30/M input and $2.50/M output. The Gemini workhorse. Cheap, fast, 1M context. Best price/performance in the Gemini lineup.
Specifications
| Provider | |
|---|---|
| Family | Gemini 2 |
| Released | 2025-04-09 |
| Status | active |
| Context window | 1.0M tokens |
| Max output | 66K 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-2.5-flash:generateContent |
| Documentation | Official docs ↗ |
| Last updated | 2026-05-29 |
What this model is good for
Based on benchmark scores and capability fit, Gemini 2.5 Flash ranks well for:
- Customer Support — rank #3. Cheapest of the Big Three. Best when you need 1M context affordably.
- Cheapest Model with Vision — rank #3. $0.30/M input but supports video too.
- Document Q&A / RAG — rank #3. Cheap and good. Best when chunks are large.
Cost calculator
For 1,000 tokens of input and 1,000 tokens of output per call, this model costs $0.0028 per call. For typical usage:
| Workload | Tokens / call (in/out) | $/call | $/1K calls | $/1M calls |
|---|---|---|---|---|
| Short Q&A | 200 / 100 | $0.000310 | $0.31 | $310 |
| Standard chat | 1K / 500 | $0.001550 | $1.55 | $1,550 |
| RAG with retrieval | 4K / 500 | $0.002450 | $2.45 | $2,450 |
| Long doc summary | 20K / 1K | $0.008500 | $8.50 | $8,500 |
| Long context (100K input) | 100K / 2K | $0.033750 | $33.75 | $33,750 |
For more precise estimates including caching discounts, use the LLM API Cost Calculator.
Other Google models
Common comparisons
- Gemini 2.5 Flash vs DeepSeek-V3 Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Flash vs GPT-5 Mini Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Flash vs Codestral Side-by-side specs, pricing, and benchmarks
- Gemini 2.5 Flash vs GPT-4o Mini Side-by-side specs, pricing, and benchmarks
API setup
curl https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "gemini-2-5-flash", "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.