Google AI Studio
unknownSelected Gemini models have free input and output token allowances. Availability and limits depend on your project, region and usage tier.
https://generativelanguage.googleapis.com/v1beta/openai
Last Probe Latency
—
Healthy Observed Days
—
Rate Limits
— RPM / — RPD
Sign-up Required
Yes
Provider status summarizes sampled models checked with the monitoring account. Your access and limits may differ.
Documentation checked: . Model availability is subject to the provider's current catalog.
Check the project limits in AI Studio. No universal RPM/RPD is claimed. Free-tier content can be used to improve Google products. Paid prices shown use standard text input; Gemini 3.8/3.6 Flash promotional prices end December 31, 2026.
Info
Models(5)
Model health is unknown until an actual check completes.
gemini-4-hydrogen
Context: Not published · $1.50/$7.50 per 1M
gemini-3.8-flash
Context: Not published · $0.750/$3.75 per 1M (promotional until 2026-12-31)
gemini-3.6-flash
Context: Not published · $0.750/$3.75 per 1M (promotional until 2026-12-31)
gemini-3.5-flash-lite
Context: Not published · $0.300/$2.50 per 1M
gemini-3.1-flash-lite
Context: Not published · $0.250/$1.50 per 1M
Quick Start
export API_KEY="your_api_key_here"
curl 'https://generativelanguage.googleapis.com/v1beta/openai/chat/completions' \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $API_KEY" \
-d '{
"model": "gemini-4-hydrogen",
"messages": [
{
"role": "user",
"content": "Hello! How are you?"
}
]
}'