NewHow we catch a seller listing the wrong model, and refund you if one does.

What is the cheapest Gemini API?

On November 20, 2026, the lowest-priced Gemini model on MartLLM is Gemini 3.1 Flash Lite at $0.00125 per million input tokens and $0.0075 per million output tokens, 99.5% below its list price. MartLLM serves 12 Gemini models through one OpenAI-compatible API; the table lists the price of each. Prices come from sellers on the MartLLM market and change during the day. MartLLM adds no fee to them.

Prices as of November 20, 2026, 11:00 UTC. This page is rebuilt every hour.

Against other providers: Cheapest Gemini API: below Google on 10 of 10 models (November 2026)

ModelInput / 1M tokensOutput / 1M tokensBelow list price
Gemini 3.1 Flash Lite$0.00125$0.007599.5%
Gemini 3 Flash Preview$0.0025$0.01599.5%
Gemini 3.5 Flash Lite$0.003$0.02599%
Gemini 3.5 Flash$0.0075$0.04599.5%
Gemini 3.8 Flash$0.0749$0.374390%
Gemini 3.1 Pro Preview$0.1096$0.657594.5%
Google: Gemini 4 Hydrogen$0.1454$0.726890.3%
Google: Gemini 4 Argon$0.1798$0.89991%
Gemini 3.7 Flash$0.1871$0.935675.1%
Google: Gemini 4 Carbon$0.1996$0.99890%
Gemini 3.6 Flash$0.2025$1.012573%
Google: Gemini 4 Neon$1.9644$9.821934.5%

MartLLM adds no fee to these prices · every model and price →

More questions

Do I need a Google Cloud account for Gemini?

No. Through MartLLM, Gemini models are called with the OpenAI SDK and a MartLLM API key.