Contact Us
Questions about Run BiOS? Comparing models, sizing a workload, or puzzled by a bill? Write to us and we will sort it out.
Send Us a Message
Fill out the form below. We reply within 24 hours on business days.
Frequently Asked Questions
Quick answers to common questions.
How does pricing work?
Inference is priced per million tokens at published input and output rates — the full rate card is in the model library. Fine-tuning runs on dedicated GPUs billed per second. The public price calculator estimates any workload before you spend anything.
What models does Run BiOS serve?
A catalog of frontier open and closed models through one OpenAI-compatible API — Claude, DeepSeek, Gemma, GLM, Kimi, MiMo, MiniMax, Nemotron, and Qwen. The model library lists every model with its context window and rates.
What is BiOS Adaptive?
One endpoint that routes each request to the best model for that task at the lowest cost, so your code stops hard-coding model IDs. Same request shape, same published rates — routing never changes what a token costs.
Do I own my fine-tuned model?
Yes. Fine-tuning runs on dedicated GPUs billed per second, and the trained weights are yours outright — exported, portable, and yours to run anywhere.
Is the API OpenAI-compatible?
Yes. Point your existing OpenAI SDK at https://api.runbios.ai/v1 with your Run BiOS key and your code works as-is. The API overview in the docs covers authentication and examples.
When will I hear back?
Within 24 hours on business days. The team is based in San Francisco, CA and works Pacific Time, Monday to Friday, 9am to 6pm PT.