Skip to main content
POST
Confirm your deployment before running this request. This page describes an API contract; a published reference does not establish hosted availability. Check the dated host report and obtain your deployment URL and credentials. Replace the example host if your provisioned service uses a different URL.
Forwards an inference request to a supported LLM provider from within the sandbox context Served by the live controller (answers 401 unauthenticated) but absent from its published /openapi.json — verified 2026-08-31.

Path parameters

string (uuid)
required
Unique sandbox identifier

Request body

InferenceRequest
string
required
LLM provider to route the request to. Allowed values: 'anthropic', 'openai', 'google'.
string
required
API path on the provider (e.g., ‘/v1/messages’).
object
required
Request body to forward to the provider.
string
Name of the stored secret containing the provider API key.
object
Additional headers to include in the provider request. Additional keys map to values of type string.

Response

InferenceResponse
integer
HTTP status code from the provider.
object
Response body from the provider.
object
Response headers from the provider. Additional keys map to values of type string.

Status codes

Using this contract

Read the source OpenAPI document for declared schemas and alternatives. This page also includes documented corrections from the spec overlays. Example IDs and values are illustrative; replace them with records from your workspace.
Last modified on September 21, 2026