BUILD WITH INFERMAX
Customer API documentation
From your first model request to compute lifecycle and usage. Start with the guide, then explore the contract.
Managed Inference
Discover entitled models, check readiness, and integrate JSON or streaming Chat Completions.
02Compute Access
Explore eligible offers, reserve capacity, and follow instance provisioning through verified release.
03Usage & Account
Understand project consumption, recorded work units, and the difference between measured and unknown usage.
Read freely. Execute with permission.
This reference is public. API requests require authorized credentials and the permissions for the selected project. Documentation does not grant access to models, capacity, or another workspace.
This site provides copyable examples and an OpenAPI download. Interactive API execution is not enabled.
Know where you are connecting
- Documentation
docs.infermax.ai- API requests
api.infermax.ai- Projects and access
console.infermax.ai
Looking for another audience?
Supplier integrations use provider-scoped APIs. Operator tools use internal operational APIs. Those private references are separate from this Customer documentation and are not published here.