Gemini 3.5 Flash

DEPRECATED 2026-10-08, stated first-party in three places read 2026-10-10: the Gemini API release notes for October 8, 2026 ('gemini-3.5-flash is deprecated and has been replaced by gemini-3.6-flash. All requests to gemini-3.5-flash are automatically routed to gemini-3.6-flash. Update your model string to gemini-3.6-flash (or gemini-3.8-flash)'), the same Deprecated caution on the model page (ai.google.dev/gemini-api/docs/models/gemini-3.5-flash), and the deprecations table, which names gemini-3.6-flash as the recommended replacement and states 'No shutdown date announced'. That row is NOT gray, so retires_on stays null and the status is deprecated, not retired. Because of the routing, a call to this model string is served by gemini-3.6-flash today. Google removed this model's section from the pricing page in the same edit (absent on the 2026-10-10 read): the price fields are the last first-party rates, read before that removal, and Google does not state which rate bills a routed request. Until 2026-10-08 it was GA/stable. Output token limit reported as 'up to 65,000' on the what's-new page; model spec convention is 65,536 - treated as 65536. The what's-new page describes additional output capabilities (images, audio, structured outputs) but the spec table for the core text model lists text output. Was listed as the recommended replacement for gemini-2.5-flash and the gemini-2.0-flash line; as of the deprecations table read 2026-07-31 that target is gemini-3.6-flash, which is cheaper on output ($7.50 vs $9.00) at the same input price. Context-caching also has a per-hour storage fee not captured here. What's-new page last updated 2026-06-24 UTC.

Source: Google official documentation ↗

Explore more

Gemini 3.5 Flash — questions & answers