RunInfra now focuses on hosted inference for agents. RunInfra Model APIs serve open-weight models through OpenAI-compatible and Anthropic-compatible endpoints.
Model APIs, pay as you go
Model API usage is billed per token at each model’s published rates. Check the model library and model pages for current availability, pricing and capabilities.
Connect your coding agent
Setup guides cover Claude Code, Codex and other coding agents. Follow the guide for your agent and installed release, including any manual steps.
Our earlier work
The Optimization agent is hidden from the public site, not deleted. Historical benchmark evidence remains on the Benchmarks page, with dates and disclosed limitations.
FAQ
Choose a model in the model library, then follow the Model APIs quickstart.
Yes. Follow the agent-specific setup guide, including any manual steps it requires.
No. Historical results do not establish current Model API performance.
References
Written by
