MODEL REFERENCE / GOOGLE

Gemini 3.8 Live
verified model reference.

Google's stable low-latency native-audio Live API model for voice agents with asynchronous function calling and multimodal inputs.

131,072context tokens
65,536max output
2026-10-12last verified

PRIMARY-SOURCE VERIFIED

Gemini 3.8 Live at a glance.

Google documents a 131,072-token context window. Input modalities: text + image + audio + video. Output: text + audio. Pricing status: Official paid API.

MODEL IDgemini-3.8-live
CONTEXT WINDOW131,072tokens
MAX OUTPUT65,536
KNOWLEDGE CUTOFFNot published
STANDARD INPUT$0.75per 1 million TEXT tokens (audio/video separate)
STANDARD OUTPUT$4.50per 1 million TEXT tokens (audio/video separate)

CAPABILITY CONTRACT

Published model behavior.

REASONING

supported

Only provider-documented reasoning controls are shown; missing controls remain unpublished rather than inferred.

INPUT

text + image + audio + video

Input modalities come from the cited official model documentation.

OUTPUT

text + audio

Output modality and output-limit claims remain separate so an undocumented token cap is not guessed.

PRICING STATUS

Official paid API.

$0.75 input · $4.50 output per 1 million TEXT tokens (audio/video separate).

SXF preserves the provider-published native billing basis. Only calculator-eligible generative token models enter token-cost arithmetic; specialist units and input-only embeddings remain visible without forced conversion.

CAVEATS

What the source record does not assume.

01

Shown Standard prices cover TEXT tokens only: $0.75 input and $4.50 output per 1M text tokens.

02

AUDIO is billed at $3.00 input and $12.00 output per 1M audio tokens (Google also publishes approximate per-minute equivalents). IMAGE/VIDEO inputs cost $1.00 per 1M tokens.

03

A free tier is listed by Google, but the catalog displays the paid-tier Standard text rates; mixed-modality voice costs are not comparable to text-only estimates.

04

Google documents no supported context caching or Batch API for this model. Its interleaved reasoning is designed to avoid reasoning-induced delay.

EXPLORE

Keep the model in context.

OFFICIAL SOURCES

Verification links.

WHAT CHANGED

Gemini 3.8 Live: what changed.

No post-baseline factual changes recorded for Gemini 3.8 Live since 2026-10-12.

VERIFIED BASELINE2026-10-12Current facts remain aligned with the SXF ledger.

VERIFIED CHANGE HISTORY

Gemini 3.8 Live verified history.

Open ledger JSON ↗
BASELINE

Gemini 3.8 Live

Baseline verified: 131,072 context · 65,536 max output · $0.75 input / $4.50 output per 1 million TEXT tokens (audio/video separate)

Official evidence ↗

Append-only SXF ledger · 1 verified event · chain head b12eeb63a07e…