gemini-3.6-flash-1009
gemini-3.6-flash is a high-efficiency model identifier in the Gemini Flash series, targeting multi-round applications where response speed and processing scale are both important. It is suitable for pre-understanding of knowledge base Q&A, work order diversion, document summarization, form field extraction, lightweight code assistance and content rewriting, etc. Prompts should provide clear roles, material scope, answer formats, and rejection criteria, and use real business samples to evaluate latency, format compliance, and Chinese language quality. Content involving transactions, legal, medical or public communication should still be reviewed by the business side.
- Context
- 1048576 tokens
- Max output
- 65536 tokens
- Input
- llm image video text-to-speech
- Output
- llm
Pricing
Input: $1.5 / 1M tokens
Output: $7.5 / 1M tokens
Cached input: $0.15000000000000002 / 1M tokens
Endpoints
- gemini
- openai