Gemini 2.5 Flash
The prior-generation fast tier, balancing speed and cost with full multimodal input. A solid default for production workloads that don't need the newest model.
At a glance
Released
Apr 17, 2025
Provider
Google
Context window
1,000,000 tokens
Max output
64,000 tokens
Modalities
Text + image + audio + video → text
Knowledge cutoff
January 2025
API model ID
gemini-2.5-flashLicense
Proprietary (API only)
Pricing
Standard
Input$0.30 / 1M
Output$2.50 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.002 on the standard tier. Run your own prompt through the calculator →
Best use cases
Production chat
Serves responsive assistants at scale with predictable cost.
Summarization
Condenses long documents and transcripts quickly.
Routing
Acts as a fast first-pass model in multi-model pipelines.
Strengths & limitations
Strengths
- Fast and affordable
- Million-token context
- Full multimodal input
Limitations
- Less capable than 3.x Flash tiers
- Older cutoff
How to test it
- No-code: open gemini.google.com and pick Gemini 2.5 Flash from the model switcher — no API key needed.
- Playground: sign in to Google AI Studio and run prompts in the workbench, then copy the generated code.
- API: create a key in Google AI Studio and call the API (example below).
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-flash:generateContent?key=$GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Explain tokenization in one paragraph."}]}]}'