Skip to content
ACS Infra
Chat

Create Chat Completion

Deprecated

POST
/v1/chat/completions

Not served: Base models have no chat format. Always answers 400, naming POST /v1/completions.

Response Body

The request is invalid: param names the field at fault, or Inference refused a value.

application/json
  1. response
error*
request_id*string

The id of the request, as in its X-Request-Id header. Send it when you report a problem.

Match^[\w-]{1,64}$
Example Request
curl -X POST 'https://api.v2.infra.acsresearch.org/v1/chat/completions'
Example Response
{  "error": {    "message": "string",    "type": "string",    "param": "string",    "code": "string",    "retryable": true,    "retry_after_seconds": 0,    "upstream_status": 0,    "request_id": "string"  },  "request_id": "string"}

Health GET

Return the state of the API in v1's shape: `ok`, `degraded` with its `degraded_reasons`, or `down`. It checks the database on its own connection, whether a pooled connection is free, and each runner, and never asks Inference. `backends` gives each served model's breaker and requests in flight, and `degraded_backends` the models whose breaker is open. 503 only when the database does not answer within `HEALTH_TIMEOUT`; a degraded API answers 200.