New Release
|
Introducing AI Stats Gateway
|
Read more in the changelog
Home
Organisations
Models
Benchmarks
API Providers
Sign In
Gemini 3.1 Pro Preview Pricing - Token Costs & Billing Details | AI Stats
Gemini 3.1 Pro Preview
Google
Overview
Family
Timeline
Benchmarks
Availability + Pricing
Quickstart
Performance
Availability + Pricing
Availability + Pricing by Provider
Performance metrics are sourced from gateway request logs in the database.
API Providers
Standard Tier
Default
Google AI Studio
Active
Latency --
Throughput --
Uptime 33.3%
Context
1.0M
Max output
66K
Input
$2
≤ 200k
$4
> 200k
Output
$12
≤ 200k
$18
> 200k
Google Vertex
Active
Latency --
Throughput --
Uptime 0.0%
Context
1.0M
Max output
66K
Input
$2
≤ 200k
$4
> 200k
Output
$12
≤ 200k
$18
> 200k