Skip to main content
fastrun serves open models on dedicated GPUs and answers through the same API as OpenAI. If your code already uses an OpenAI SDK, switching takes three changes: the base URL, the API key and the model name.

Quickstart

Make your first request in a couple of minutes.

Models

What is served, with its limits and features.

Streaming

Show tokens as they are generated.

API reference

Every endpoint and parameter.

​
What you get

  • Speed. Gemma 4 31B runs on NVIDIA B200 GPUs with speculative decoding. In our own measurement, one request at a time without network time, the median time to first token was 24 ms and the median output speed was 280 tokens per second. Latency rises under heavy load.
  • OpenAI compatibility. Chat completions, streaming, tool calling, JSON output and reasoning work with the official OpenAI SDKs and the tools built on them.
  • Pay per token. You pay for input and output tokens only, with a lower price for input that is served from the prompt cache. See Pricing.