Model Metadata
- type
- realtime
- name
- Gemini 3.1 Flash Live Preview
- description
- High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications
- family
- gemini-flash
- open weights
- No
- knowledge
- 2025-01
- release date
- 2026-03-26
- modalities
- input: text, image/jpeg, image/png, video, audio/pcm; output: text, audio/pcm
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; temperature: Yes; top_p: Yes; top_k: Yes
- limit
- context: 131,072; output: 65,536
Provider Variants 1
Google gemini-3.1-flash-live-preview
Context 131,072 · Output 65,536
- type
- realtime
- name
- Gemini 3.1 Flash Live Preview
- description
- High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications
- family
- gemini-flash
- open weights
- No
- knowledge
- 2025-01
- release date
- 2026-03-26
- modalities
- input: text, image/jpeg, image/png, video, audio/pcm; output: text, audio/pcm
- capabilities
- tools: supported: Yes; reasoning: supported: Yes; default: type: effort; value: minimal; effort: minimal, low, medium, high; cache: No; structured_output: No; temperature: Yes; top_p: Yes; top_k: Yes; system_updates: No; effort_updates: No
- limit
- context: 131,072; output: 65,536
- id
- gemini-3.1-flash-live-preview
- canonical id
- google/gemini-3.1-flash-live-preview
- last updated
- 2026-03-26
- api
- bidi-generate-content: base_url: https://generativelanguage.googleapis.com/v1beta; sdk: aisdk: @ai-sdk/google; capabilities: tools: updates: No