Google / SOURCE-LINKED MODEL RECORD

Gemini 3.8 Live

Gemini 3.8 Live

Hosted modelverifiedObserved Oct 13, 2026
Input types
text, image
Output types
text
Observed context window
131,072
Source release date
Sep 15, 2026

Know the exact model.

The canonical record is google:gemini-3.8-live. Capabilities and context limits reflect source observations; the limits of a particular inference endpoint may differ.

Inclusion in the radar does not mean this model is served by Flonno. For the model currently available through our API, see Qwen3.8 Flash 27B and API pricing.

Artifact evidence

gemini-3.8-live

official api · Mutable source entry · Gemini API; region and account dependent. First observed Sep 15, 2026; last observed Oct 13, 2026.

Open original artifact source ↗

gemini-3.8-live

official changelog · Mutable source entry · Official provider announcement. First observed Sep 15, 2026; last observed Oct 10, 2026.

Open original artifact source ↗

Evaluate it for your workflow.

Pin the artifact and inference configuration. Use representative inputs with a written answer rubric, then record accepted results, errors, complete request time and token usage. Keep output budgets and concurrency explicit.

Benchmark results apply to their recorded version and method. They do not transfer automatically to a different runtime or a quantized derivative.

Explore practical comparison guides →

Benchmark provenance

Read the methodology →

No source-linked benchmark measurements are available for this exact model artifact.

Verified lifecycle updates

Source publication date
Google / general availability

Google Gemini 3.8 Live is generally available

Google hat Gemini 3.8 Live und Gemini 3.8 Live Extended Thinking als Audio-zu-Audio-Modelle für die Live-API allgemein verfügbar gemacht. Die Modelle ermöglichen echtzeitfähige Sprachassistenten mit geringer Latenz und bieten Funktionen wie verschachteltes Denken sowie asynchrone Funktionsaufrufe.

AI-assisted summary · gemini-3.7-flashRecorded Sep 15, 2026