← Back to Documentation
Models & Providers
OpenAI Integration
Connect OpenAI models and expose approved options through the provider catalog.
Key Steps
- Create an organization-owned OpenAI API key and store it securely.
- Add the provider configuration and select the models your users should see.
- Track usage separately so finance can understand OpenAI-specific spend.
Article Scope
This guide focuses on the operational steps needed to run Orchestris with team access, provider control, and predictable usage.
Visual Reference
Provider setup
- Use a service-owned API key instead of a personal key.
- Add the OpenAI provider in the catalog and test connectivity.
- Map approved model IDs to readable aliases for users.
Policy decisions
- Decide which teams can use higher-cost models.
- Set quota expectations before broad access.
- Document acceptable prompt and data handling practices.
Monitoring
- Review provider health after rollout.
- Track request volume and estimated cost by model.
- Rotate keys if usage appears outside expected business patterns.
Related Topics
Models & Providers
Using AI Models
Help users choose the right models without exposing provider complexity.
Models & Providers
Anthropic Integration
Connect Anthropic models for teams that need strong long-context and reasoning workflows.
Models & Providers
Local Model Integration
Connect llama.cpp, OpenAI-compatible gateways, or other production-ready internal model endpoints.