llm11

Google Gemini models

llm11 can call 20 Google Gemini models through one API, with Jev, TypeSafe AI's System One model, deciding which one answers each request. Blended prices run from $0.063 to $4.50 per million tokens. The newest is Gemini 3.8 Flash, released 2026-09-02.

Google Gemini models with live prices
ModelInput / 1MOutput / 1MContext
Gemini 3.8 Flash$0.750$3.751.05M
Gemini 3.7 Flash$0.750$3.751.05M
Gemini 3.5 Flash Lite$0.300$2.501.05M
Gemini 3.6 Flash$0.750$3.751.05M
Gemini 3.5 Flash$1.50$9.001.05M
Gemini 3.1 Flash Lite$0.250$1.501.05M
Gemma 4 26B A4B $0.090$0.300262K
Gemma 4 31B$0.090$0.340262K
Gemini 3.1 Flash Lite Preview$0.250$1.501.05M
Gemini 3.1 Pro Preview Custom Tools$2.00$121.05M
Gemini 3.1 Pro Preview$2.00$121.05M
Gemini 3 Flash Preview$0.500$3.001.05M
Gemini 2.5 Flash LiteRetires 2026-10-20$0.100$0.4001.05M
Gemini 2.5 FlashRetires 2026-10-20$0.300$2.501.05M
Gemini 2.5 ProRetires 2026-10-20$1.25$101.05M
Gemini 2.5 Pro Preview 06-05$1.25$101.05M
Gemma 3 12B$0.050$0.150131K
Gemma 3 4B$0.050$0.100131K
Gemma 3 27B$0.080$0.450131K
Gemma 2 27B$0.650$0.6508K

Read from the live catalogue and refreshed daily. Prices are per million tokens.

Questions

Which Google models can I call through llm11?
20 today, listed with live prices on this page. The list follows the upstream catalogue, so a new Google model appears here without anyone editing the page.
What is the cheapest and the most expensive Google model?
By blended price, weighting three parts input to one part output: Gemma 3 4B is cheapest at $0.063 per million tokens, and Gemini 3.1 Pro Preview is the most expensive at $4.50.
What is the newest Google model?
Gemini 3.8 Flash, released 2026-09-02. Call it with model set to google/gemini-3.8-flash.

Other labs