Context
1.0M
Input
$0.75/M
Output
$3.75/M
Aliases:gemini-3-8-flashgoogle-gemini-3.8-flashgoogle-gemini-3-8-flashgemini-flash-3.8gemini-flash-3-8
Google's Flash model for agentic and multimodal work: thinking, search grounding, code execution, and computer use over a 1M-token context.
ai-studio/gemini-3.8-flashQuantUnspecified
- Input
- $0.75/M
- Output
- $3.75/M
- Context
- 1.0M
- Max out
- 66K
- Cache read
- $0.07/M
- Cache write
- $0.75/M
- Thinking out
- $3.75/M