Gemini 2.5 Flash Preview 09-25
RetiredA Google model with a 1M-token context window, image input and tool calling. Released on the Gemini API September 25, 2025, now retired.
Access details: Gemini API
A pinned version. Requests to this ID always get the same model.
gemini-2.5-flash-preview-09-25Updated Sep 23, 2026
Capabilities & limits
- Context window
- 1M
- Maximum output
- 64K
- Image input
- Supported
- Tool calling
- Supported
- Structured output
- Supported
Pricing
USD / 1M tokens- Input
- No longer sold
- Output
- No longer sold
No longer sold on the Gemini API.
Price history
Feb 17, 2026
Input No longer sold per million tokens
Feb 17, 2026
Output No longer sold per million tokens
Technical details
- Parameters
- Not published
- Active parameters
- Not published
- Architecture
- Sparse mixture-of-experts (MoE) transformer with native multimodal support for text, vision, and audio (Gemini 2.5 family)
- Training / knowledge cutoff
- January 2025
- Input modalities
- Text, image, video, audio
- Output modalities
- Text
From Google
Official announcement ↗Release & lifecycle
- First available
- Sep 25, 2025
- retired
- Feb 17, 2026