Gemini 2.5 Pro
The prior-generation high-end Gemini, still a capable all-rounder for reasoning, code and long-context work. A dependable choice when the latest flagship isn't required.
At a glance
Released
Mar 25, 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-proLicense
Proprietary (API only)
Pricing
Standard
Input$1.25 / 1M
Output$10 / 1M
Long-context requests are billed at $2.50 in / $15 out per 1M. A typical 1,500-token prompt with a 650-token answer costs ≈ $0.008 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withGemini 2.0 Pro (February 2025)
- Stronger reasoning and coding than the 2.0 line
- Superseded on the frontier by the Gemini 3 and 4 families
Best use cases
General reasoning
Handles analysis, coding and writing across long inputs reliably.
Document Q&A
Answers questions over large document sets with its million-token window.
Multimodal tasks
Processes images, audio and video for mixed-media workflows.
Strengths & limitations
Strengths
- Well-rounded capability
- Large context window
- Mature and stable
Limitations
- Older knowledge cutoff
- Outpaced by newer flagships
How to test it
- No-code: open gemini.google.com and pick Gemini 2.5 Pro from the model switcher — no API key needed.
- Playground: sign in to Google AI Studio and run prompts in the workbench, then copy the generated code.
- API: create a key in Google AI Studio and call the API (example below).
curl "https://generativelanguage.googleapis.com/v1beta/models/gemini-2.5-pro:generateContent?key=$GEMINI_API_KEY" \
-H "Content-Type: application/json" \
-d '{"contents": [{"parts": [{"text": "Explain tokenization in one paragraph."}]}]}'