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

More models

  • vertex/gemini-3.7-flash
  • gpt-5
  • gemini-3.1-pro-preview-0930
  • gpt-5.3-codex

    gpt-5.3-codex 是 OpenAI 面向代理式软件工程的 Codex 模型标识。官方模型目录将 Codex 系列用于长链路编码任务,例如理解代码库、规划修改、编辑多文件、运行测试、排查错误和调用开发工具。它适合在明确仓库范围、测试标准和变更约束下协助研发工作。调用时应提供项目结构、语言版本、依赖、允许访问的工具和不可修改区域,并将生成的变更置于版本控制、自动化测试和安全审查之下。