Gemini 3.8 Flash

gemini-3.8-flash

Highly capable reasoning for long-horizon agentic workflows

Intelligence: 40.9
Context: 1.04M
Training cutoff: --
Added: 2026-09-03
Inputs: Vision

Providers

One route serves Gemini 3.8 Flash, and every figure below is measured on it. Where the selected window has too little traffic, the figure names what it is based on instead.

Google AI Studio only route

gemini-3.8-flash

Uptime

100.0%

Input / 1M: $0.75
Output / 1M: $3.75
TTFT: 1.86s fixed prompt · n=8
Output rate: 139.1 tok/s fixed prompt · n=8

1.04M context 65,536 max output cache $0.075 read / $0.75 write per 1M VisionRetention 55 days Training No Provider terms, reviewed 2026-10-13warming · 30m

Prompt caching Automatic reuse Eligible Cache key Ignored Caller breakpoints None advertised

TTFT is the median time to the first visible answer token over real ModelRelay requests, with a fixed prompt standing in for models that have no traffic yet. Speed ranks by it. Intelligence is the Artificial Analysis Intelligence Index.