AI Model Watch
Models / Google

Gemini 3.8 Flash-Lite TTS

GA

Text-to-speech model: text in, audio out. GA per Google's September 22, 2026 release note, which describes it as a 'fast, cost-efficient TTS model built to replace gemini-3.1-flash-tts-preview for high-throughput production and real-time voice agent cascades'. THE PRICE FIELDS CARRY THE COLUMN IN FORCE THROUGH 2026-12-31, not the 2027 one: paid-tier Standard per 1M tokens is $0.50 input (text) / $6.00 output (audio) / $0.125 context caching through December 31, 2026, doubling to $1.00 / $12.00 / $0.25 starting January 1, 2027. Other tiers on the same two dates: Batch $0.25 / $3.00 (caching $0.0625) then $0.50 / $6.00 (caching $0.125); Flex $0.25 / $3.00 (caching $0.025) then $0.50 / $6.00 (caching $0.05); Priority $0.90 / $10.80 (caching $0.225) then $1.80 / $21.60 (caching $0.45). Cache storage, which this schema has no field for, is $0.50 per 1M tokens per hour through 2026-12-31 and $1.00 from 2027-01-01. Free tier is 'Free of charge' on Standard and Priority and 'Not available' on Batch and Flex. Audio tokens are billed at 25 tokens per second of audio. Input is priced the same as gemini-3.8-flash-tts; the difference is output, two-thirds of that model's audio rate. The model page gives an 8,192-token input limit and a 16,384-token output limit, text in and audio out, 101 input languages auto-detected, caching supported, and no thinking, function calling, grounding or Live API; Batch, Flex and Priority are all supported. Released 2026-09-22 per both the release note and the deprecations table ('No shutdown date announced', row not gray); the model page's 'Latest update' field says July 2026, which is coarser and older, so it is not used. Google publishes no knowledge cutoff. Added 2026-09-24, two days after launch.

Gemini 3.8 Flash-Lite TTS by Google costs $0.5 per 1M input tokens and $6 per 1M output tokens ($1.88/1M blended), with a 8K (8192-token) context window. It is generally available (GA).

Last verified: 26 Sep 2026 · sourced from official provider documentation

Provider
Google
Status
GA
Input price
$0.5 / 1M tokens
Output price
$6 / 1M tokens
Cached input
$0.125 / 1M tokens
Blended price
$1.88 / 1M tokens
Context window
8192 tokens (8K)
Max output
16.384 tokens
Modality
text, audio-out
Open weights
No — API only
Knowledge cutoff
—
Released
22 Sep 2026
API string
gemini-3.8-flash-lite-tts

Source: Google official documentation ↗

See also

Explore more

All Google models→

Prices, context windows and lifecycle status for every Google model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Gemini 3.8 Flash-Lite TTS — questions & answers

How much does Gemini 3.8 Flash-Lite TTS cost?

Gemini 3.8 Flash-Lite TTS is priced at $0.5 per 1M input tokens and $6 per 1M output tokens ($1.88/1M blended at a 3:1 input-to-output ratio), with cached input at $0.125 per 1M tokens.

What is the context window of Gemini 3.8 Flash-Lite TTS?

Gemini 3.8 Flash-Lite TTS has a 8192-token context window (8K), with up to 16.384 output tokens per request.

Is Gemini 3.8 Flash-Lite TTS deprecated?

No — Gemini 3.8 Flash-Lite TTS is generally available (GA) and not currently scheduled for deprecation or retirement in our tracker.

Does Gemini 3.8 Flash-Lite TTS support image or vision input?

Our catalog lists Gemini 3.8 Flash-Lite TTS's modalities as text, audio-out; image/vision input is not among them.

Can I self-host Gemini 3.8 Flash-Lite TTS?

No — Gemini 3.8 Flash-Lite TTS is proprietary. Its weights are not publicly released, so it is available only through Google's API (or hosted partners), not for self-hosting.

What is the API model string for Gemini 3.8 Flash-Lite TTS?

The API model identifier for Gemini 3.8 Flash-Lite TTS is "gemini-3.8-flash-lite-tts" when calling Google's API.