On October 31, 2026, the cheapest GPT-OSS 120B API we found is UberLLM: buyers paid a median of $0.00014 per million input tokens and $0.0006 per million output tokens over the last 24 hours. That is at least 99.6% less on both input and output than the closest other provider we checked, Requesty ($0.032 and $0.14). DeepInfra, Novita AI, Vercel AI Gateway and OpenRouter are higher still. UberLLM adds no fee to these prices, and a request that fails is not billed.
Prices as of October 31, 2026, 18:00 UTC. This page is rebuilt every hour.
Use the OpenAI SDK or any OpenAI-compatible client: set the base URL to the UberLLM endpoint, use an UberLLM API key and set the model to "openai/gpt-oss-120b". The Anthropic SDK works too, through /v1/messages.
Why is GPT-OSS 120B cheaper on UberLLM?
UberLLM is a market: sellers offer GPT-OSS 120B capacity below its list price, and each request goes to a seller that can serve it. A request costs what its seller charged, UberLLM adds no fee to it, and every request is listed with its cost in Activity.
Can a request cost more than this price?
Yes, when the lower-priced sellers are busy. Send provider.max_price with the most you will pay per million tokens: the request only goes to sellers at or under it and is never billed above it.
Are there other fees?
UberLLM adds no fee to model prices. A card fee of 5.5% + $0.50 is added when you buy credit. With the 5.5% added, UberLLM's GPT-OSS 120B price is still lower than every other provider in the table.