Model prices / Google

Gemini 3.8 Flash API pricing

Official API pricing for Gemini 3.8 Flash (Google) on Gemini API (Google AI Studio): cache and off-peak prices, context length, open weights and regional availability, with sources and check dates.

Context: 1.05M
Max output: 66K
Open weights: No
Current version: —

GLOBAL · USD Gemini API (Google AI Studio)

gemini-3.8-flash

Tier	Input	Cached input	Cache write	Output
Standard	$0.75≈¥5.015	$0.075≈¥0.501	—	$3.75≈¥25.07

Mainland China NoOutside China YesOfficial payment Card, Bank account

per 1M tokens · Source 2026-10-17

Paid-tier Standard price valid through 2026-12-31; from 2027-01-01 it rises to $1.50 input, $0.15 cached, $7.50 output. Output price includes thinking tokens. Cache storage $0.50 per 1M tokens per hour ($1.00 from 2027). Free tier available; Batch/Flex/Priority not listed

Source

https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash · 2026-10-17

≈ marks values converted at the ECB reference rate, for comparison only; the published currency is authoritative.