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

What is the cheapest Llama API?

On October 31, 2026, the lowest-priced Llama model on UberLLM is Llama 3.2 3B at $0.0296 per million input tokens and $0.1952 per million output tokens, 41% below its list price. UberLLM serves 4 Llama models through one OpenAI-compatible API; the table lists the price of each. The largest discount is on Llama 3.3 70B Instruct, 52% 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.

Get an API keySee all models and prices
base_url = "https://api.uberllm.dev/v1"
ModelInput / 1M tokensOutput / 1M tokensBelow list price
Llama 3.2 3B$0.0296$0.195241%
Llama 3.3 70B Instruct$0.0479$0.153352%
Llama 3.2 3B (Morpheus Web)$0.1125$0.45
Llama 3.3 70B (Morpheus Web)$0.525$2.10

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