NewPoint any agent at UberLLM — one key, every model, list price or less.

What is the cheapest Gemma API?

On October 31, 2026, the lowest-priced Gemma model on UberLLM is Gemma 3 4B IT at $0.000462 per million input tokens and $0.0009 per million output tokens, 99% below its list price. UberLLM serves 11 Gemma models through one OpenAI-compatible API; the table lists the price of each. The largest discount is on Gemma 4 31B, 99% below its list price. Prices come from sellers on the UberLLM market and change during the day. UberLLM adds no fee to them.

Prices as of October 31, 2026, 18:00 UTC. This page is rebuilt every hour.

base_url = "https://api.uberllm.dev/v1"
ModelInput / 1M tokensOutput / 1M tokensBelow list price
Gemma 3 4B IT$0.000462$0.000999%
Gemma 3 12B IT$0.0005$0.001599%
Gemma 4 26B A4B IT$0.000675$0.0022599%
Gemma 4 31B$0.00096$0.0028899%
Gemma 4 E2B$0.00198$0.0039695%
Gemma 4 31B IT$0.00324$0.0097297%
Gemma 3 27B$0.0188$0.047176%
Gemma 3 27B E2EE$0.056$0.20
Gemma 4 31B (E2EE)$0.10$0.30
Gemma 4 26B A4B IT (Morpheus Web)$0.1219$0.375
Gemma 4 31B IT (Morpheus Web)$0.1313$0.375

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