Plain-English Summary
A live conversational model that can listen, see, speak, and respond in real time.
Gemini 3.1 Flash Live Preview
A live conversational model that can listen, see, speak, and respond in real time.
Gemini Live
Multimodal LLM
Preview
Open weights: No
API: Yes
Technical Notes
Streaming native-multimodal model accepting text, images, audio, and video and producing text or audio with 131K context.
Best For
Voice agents, live assistants, video understanding, interactive experiences
Watch Out For
Preview; real-time systems require careful latency, interruption, and safety design.
Model Specs
- Maker
- Country
- Not listed
- Family
- Gemini Live
- Type
- Multimodal LLM
- Release date
- 2026-03-01
- Date confidence
- Month / latest update
- Status
- Preview
- Context window
- 131,072 tokens
- Max output
- 65,536
- Parameters
- Not disclosed
- Active parameters
- Not disclosed
- Architecture
- Proprietary streaming multimodal transformer
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Limited / endpoint dependent
- API available
- Yes
- Open weights
- No
- Self-hostable
- No
- License
- Proprietary
- Inputs
- Text, image, audio, video
- Outputs
- Text, audio
- Approx. price
- See provider pricing
- How to access
- Provider website or API
- Model / API ID
- gemini-3.1-flash-live-preview
- Knowledge cutoff
- 2025-01
- Fine-tuning
- Prompting / RAG
- Completeness
- 90 %
- Verified
- Jul 18, 2026
- Snapshot date
- Jul 18, 2026
- Source
- Official source