Skip to content
llmprice

Gemini 3.1 Pro Preview Custom Tools

Updated Sep 11, 2026

gemini-pro1.0M context66k max outputreleased Feb 19, 2026ReasoningTool calling
Cheapest input
$2
Cheapest output
$12
Official (Google)
$12
output per 1M tokens
Providers
11
offering this model
Spread
1.0×
max / min output

Offers

Metered per-token prices. Cheapest input and output are highlighted; marks a context-tier surcharge.

Provider1M input1M output1M cache read1M cache writeContext
AIHubMixCheapest$2Cheapest$12$0.21.0M
Databricks$2$12$0.21.0M
Eden AI$2$12$0.2$0.3751.0M
Google$2$12$0.21.0M
Vertex$2$12$0.21.0M
Kilo Gateway$2$12$0.2$0.3751.0M
Merge Gateway$2$12$0.21.0M
NanoGPT$2$12$0.2$0.3751.0M
Neon$2$12$0.21.0M
OpenRouter$2$12$0.2$0.3751.0M
OrcaRouter$2$12$0.21.0M

Other gemini-pro models