Providers API

List the upstream backends AnyRouter can dispatch requests to.

List the upstream backends AnyRouter routes through, each with a logo and short description. This is separate from the model catalog at /api/v1/models, which lists model ids.

Public: no authentication required.

Request

GET /api/v1/providers takes no parameters or auth headers and always returns the full list. To see which providers serve one model, fetch /api/v1/models/:id and read its upstreams[] array.

Response

{
  "object": "list",
  "data": [
    {
      "id": "anthropic",
      "name": "Anthropic",
      "description": "Anthropic's Claude model family.",
      "logo": "/providers/anthropic.svg"
    },
    {
      "id": "openai",
      "name": "OpenAI",
      "description": "OpenAI-hosted GPT and embedding models.",
      "logo": "/providers/openai.svg"
    },
    {
      "id": "cloudflare",
      "name": "Cloudflare AI Gateway",
      "description": "Cloudflare's Workers AI catalog (first-party + partner-hosted).",
      "logo": "/providers/cloudflare.svg"
    }
  ]
}
FieldTypeDescription
idstringStable backend identifier. Matches the provider field on /api/v1/models entries.
namestringDisplay name.
descriptionstringShort summary (≤ 200 chars), safe to render in tooltips.
logostringAbsolute or root-relative path to an SVG asset.

Availability is not returned here; it lives on /api/v1/health so this catalog can be cached.

Examples

curl https://anyrouter.dev/api/v1/providers

Errors

StatusCodeMeaning
429too_many_requestsRate limited.
500internal_server_errorUnexpected AnyRouter failure.
502bad_gatewayCatalog generation failed (rare; falls back to cached copy).
503service_unavailableService is down.

AnyRouter routes requests to third-party models. Models and outputs are provided as is, with no warranty; you use them at your own risk. Disclaimer