OhMyGPT
Models

Get recent model availability

GET
/v1/models/{creator}/{model}/availability

Answers whether the model works right now and when it had trouble over the last 72 hours, when you leave the provider choice to the gateway and for each provider that served it. Counted the same way as /v1/models/{creator}/{model}/stats: auto counts each request that left the provider choice to the gateway by the result the caller received; each provider counts every upstream attempt it was sent, which is what a request naming that provider gets. Only rates and minute counts are published.

Path Parameters

creator*string
model*string

Response Body

Successful response

application/json
  1. response
as_of*string
Formatdate-time
auto*

Requests that left the provider choice to the gateway.

model_id*string
providers*array<>

Providers with upstream attempts in the 72 hours, sorted by name.

Example Request
curl -X GET 'https://api.ohmygpt.com/v1/models/string/string/availability'
Example Response
{  "as_of": "2019-08-24T14:15:22Z",  "auto": {    "affected_minutes": 0,    "hourly": [      {        "affected_minutes": 0,        "time": "2019-08-24T14:15:22Z",        "uptime_pct": 0      }    ],    "status": "operational",    "uptime_pct": 0  },  "model_id": "string",  "providers": [    {      "affected_minutes": 0,      "hourly": [        {          "affected_minutes": 0,          "time": "2019-08-24T14:15:22Z",          "uptime_pct": 0        }      ],      "status": "operational",      "uptime_pct": 0,      "provider": "string"    }  ]}

Retrieve model GET

Returns detailed information about a specific model. Model IDs use the `{creator}/{model}` form, so clients must send both path segments, for example `/v1/models/openai/gpt-4o`.

Get model endpoints GET

Lists the provider endpoints that serve a model, cheapest first, with their price, limits, availability and recent measurements in OpenRouter's format. Measurements come from real traffic, are refreshed about once a minute, and are null until an endpoint has enough samples (see each field). Rate limited per IP.