Choose a model for the work you need to doMe
Model specifications and sources
Google 官方 Gemini API 型号，支持 text, images, audio, video Input与 text, audio Output。 Input上限 131,072 tokens。 Output上限 65,536 tokens。
- Context window
- 131,072 tokens
- Maximum input
- 131,072 tokens
- Maximum output
- 65,536 tokens
- Input modalities
- Text, Image, Audio, Video
- Output modalities
- Text, Audio
- Default snapshot
- Not published / unverified
- Documentation checked
- 2026-09-24
- Automatic model identity check
- https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview：URL is outside the configured official host；https://ai.google.dev/gemini-api/docs/models/gemini-3.1-flash-live-preview：HTTP 404；https://ai.google.dev/llms.txt：HTTP 404；https://ai.google.dev/sitemap.xml：HTTP 404 · 2026-11-11
- Next automatic check
- 2026-11-12T09:11:56.892Z
- Identity check source
- Official evidence page ↗
- Documentation source
- View source ↗
Model recordOfficial documentation未确认Official website未明确服务区域
Google 官方 Gemini API 型号，支持 text, images, audio, video Input与 text, audio Output。 Input上限 131,072 tokens。 Output上限 65,536 tokens。
Writing & chatVision & OCRSpeech to textText to speech
Only catalog information is available. The API base URL, request path and authentication have not been verified, so no executable configuration is provided.
API BASE URLNo data available
Model ID
gemini-3.1-flash-live-previewRequest method / pathNo data available
AuthenticationNo data available
Visit the provider website or documentation for integration details