Gemini 3.8 Flash

google/gemini-3.8-flash

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Modalities
Text
Image
Video
File
Audio
In / Out price
$0.75 / $3.75 per 1M
Context
1.05M · 66K out
Released
Sep 2, 2026

Providers

Live list prices and uptime across 6 providers serving this model.

ProviderInput /MOutput /MCache read /MContextMax outputUptime 24h
Google AI Studio$0.375$1.875$0.0371.05M66K99.89%
Google$0.375$1.875$0.0371.05M66K78.08%
Google AI Studio$0.75$3.75$0.0751.05M66K99.92%
Google$0.75$3.75$0.0751.05M66K97.91%
Google AI Studio$1.35$6.75$0.1351.05M66K99.77%
Google$1.35$6.75$0.1351.05M66K99.66%

Implicit prompt caching available — repeated context bills at the cache read rate.

Capabilities

Tool calling
Reasoning
Include reasoning
Max tokens
Reasoning effort
Response format
Seed
Stop
Structured outputs
Temperature
Tool choice
Top P

Pricing detail

Input
$0.75
Output
$3.75
Cache read
$0.075
Cache write
$0.042

USD per 1M tokens.