OhMyGPT
Status

Retrieve incident

GET
/v1/status/incidents/{id}

Returns a public incident and its update timeline when the incident is active or resolved within the last 30 days.

Path Parameters

id*string

Response Body

Successful response

application/json
  1. response
data*
success*boolean
Example Request
curl -X GET 'https://api.ohmygpt.com/v1/status/incidents/string'
Example Response
{  "data": {    "incident": {      "acknowledged_at": "2019-08-24T14:15:22Z",      "affected_components": [        "string"      ],      "created_at": "2019-08-24T14:15:22Z",      "id": "string",      "resolved_at": "2019-08-24T14:15:22Z",      "severity": "string",      "status": "string",      "title": "string",      "updated_at": "2019-08-24T14:15:22Z"    },    "updates": [      {        "body": "string",        "created_at": "2019-08-24T14:15:22Z",        "id": "string",        "status": "string"      }    ]  },  "success": true}

Rerank documents POST

Orders documents by how relevant each is to a query, in the Cohere and Jina rerank format. `model`, `query` and `documents` are read; every other field (`top_n`, `return_documents`, `max_tokens_per_doc` and so on) is passed to the model unchanged, and the response is the model's own. Billed per query or per token, whichever the model's price in `GET /v1/models` lists.

Get model route time series GET

Returns route-level success rate, latency, and TTFT time series for one model. A bucket's success_rate is null until it has at least 20 requests; its latency fields are omitted until it has at least 30 requests, and its TTFT fields until it has at least 30 first-token samples.