Gemini 3.1 Flash Live Preview

Tool callingReasoningImage inputAudio inputAudio outputVideo input

Website

High-quality, low-latency Live API model for real-time dialogue and voice-first AI applications

Released: 6mo ago
Pricing: Not published

Sources:models.dev

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

No benchmark results have been matched to this model yet.

Specifications

Developer: Google DeepMind
Model family: Gemini
Type: Audio model
Predecessor: —
Successor: —
Released: March 26, 2026
Model ID: google/gemini-3.1-flash-live-preview
Openness: Closed
License: —
Input modalities: text, image, video, audio
Output modalities: text, audio
Modality: text+image+video+audio->text+audio
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: google/gemini-3.1-flash-live-preview
Source family: gemini-flash
Last updated: 2026-03-26
Knowledge cutoff: 2025-01
Model context: 131K
Model output limit: 66K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: No
Temperature control: Yes

Complete source record (JSON)

{
  "id": "google/gemini-3.1-flash-live-preview",
  "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",
  "last_updated": "2026-03-26",
  "knowledge": "2025-01",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": false,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image",
      "video",
      "audio"
    ],
    "output": [
      "text",
      "audio"
    ]
  },
  "limit": {
    "context": 131072,
    "output": 65536
  },
  "release_date": "2026-03-26",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider-specific media pricing is not available in the imported source data yet.

Text provenance

Gemini app/web

Google SynthID text watermarking

Google DeepMind says text generated in the Gemini app and web experience is watermarked with SynthID by adjusting token probabilities.

Official explanation