Gemini API

AI / ML

Google

Multimodal AI models supporting text, image, video, and code across the Gemini model family

Reported Latency

Typical performance from public reports -- not live measurements

Average: 920ms
p50
650ms
p95
2,400ms
p99
5,000ms

Reliability

99.85%observed uptime

Pricing

Free tier

15 RPM free tier

Paid starts at

$0.075 / 1M input tokens (Flash)

Technical Details

Authentication

API Key

Rate limit

360 RPM (paid)

Protocols

RESTgRPC

SDKs

PythonNode.jsGoSwiftKotlin

Regions

USEUAsia-Pacific
DocumentationBase URL

Last updated: 2026-04-12