Gemini 2.5 Flash Live (Native Audio)

Live API model with native-audio reasoning. Rates differ per input type: input $0.50 (text) / $3.00 (audio or video); output $2.00 (text) / $12.00 (audio). Values shown are the TEXT tier. Until 2026-10-06 Google stated "No shutdown date announced" while already naming a recommended replacement, so the pointer was recorded and the status held at preview (never infer a lifecycle change the provider has not declared). On the 2026-10-07 read Google's deprecations table publishes a shutdown date of November 17, 2026 for this endpoint (row not grey, so it is still running); status is therefore deprecated and retires_on carries that date. Google publishes shutdown dates as "the earliest possible dates on which a model might be retired". RE-POINTED 2026-09-16: until then that replacement was gemini-3.1-flash-live-preview, read from the deprecations table on 2026-08-19; on 2026-09-15 Google re-pointed it to gemini-3.8-live, and that is what the table states today. Google's current models page publishes no input/output token limits for this endpoint (read 2026-08-19), so context_window and max_output_tokens are null rather than carried over from a page that no longer states them. Lifecycle read first-party from Google's deprecations table on 2026-08-19.

Source: Google official documentation ↗

Explore more

Gemini 2.5 Flash Live (Native Audio) — questions & answers