Cheapest Gemini API: below Google on 10 of 10 models (November 2026)
Updated November 20, 2026, 11:00 UTC. MartLLM prices are read live when the page is built (every hour); other providers' prices were checked November 19, 2026 or read from their public price lists at build. MartLLM wrote this page and is one of the providers in it.
On November 20, 2026, MartLLM was below Google’s own price on both input and output for 10 of the 10 Gemini models we compared, with MartLLM’s card fee added. Among the real-time prices in the table, MartLLM was lowest on 12 of the 12 models. Google’s Batch API halves its price for jobs that can wait, and beats MartLLM on Gemini 4 Neon. MartLLM prices are the best seller’s price now; they move during the day.
Some MartLLM prices here are more than 70% below list. They are what buyers were billed, not errors. Why so cheap?
Against Google’s price: the same on 9, higher on 1 of 10
MartLLM first, then Google’s own API, then the other providers that list these models. The table below shows, model by model, who is lowest. An empty cell means we could not confirm it on the provider's own pages.
Gemini prices, model by model ($ per 1M input / output tokens)
MartLLM: the best seller’s price, read November 20, 2026; the 5.5% card fee is not in the cell. Google: its own pricing page, checked November 19, 2026; an empty cell means its page does not list that model. Gemini 3.8 Flash goes to $1.50 / $7.50 at Google on January 1, 2027. Gemini 4 Carbon goes to $4.00 / $20.00 at Google on December 1, 2026. Gemini 4 Argon goes to $4.00 / $20.00 at Google on December 1, 2026. Gemini 3.6 Flash goes to $1.50 / $7.50 at Google on January 1, 2027. Google Batch: 50% of its standard price, as its page states. OpenRouter, Vercel AI Gateway and Requesty: each one’s public model list, read when this page was built.
Pick it if: You want Gemini below Google’s price, billed per request with no plan, and the same key for every other model.
Watch for: Requests go to third-party providers, not to Google directly: if you need Google’s own data terms, use its API. The price is a market price and can be higher when the lower-priced sellers are busy (cap it with provider.max_price).
Yes, for testing. Google’s free tier covers models such as Gemini 4 Hydrogen, Gemini 3.8 Flash and the Flash Lite models; Gemini 3.1 Pro Preview, Gemini 4 Argon, Carbon and Neon are paid only.
Is the Gemini Batch API cheaper?
Yes. Google’s paid tier lists the Batch API at a 50% cost reduction. Results are asynchronous, so it suits offline jobs, not chat.
What happens to Gemini 2.5 Pro and 2.5 Flash?
Google’s pricing page says that from December 1, 2026, requests to gemini-2.5-pro go to Gemini 3.8 Flash and requests to gemini-2.5-flash go to Gemini 3.5 Flash-Lite.
Can I cap what a Gemini request costs on MartLLM?
Yes. Send provider.max_price with the most you will pay per million tokens; the request only goes to sellers at or under it.
Are there other fees on MartLLM?
No MartLLM fee on requests. Adding credit by card costs 5.5% + $0.50.