AALLM Docs

Providers API

List direct labs, cloud platforms, gateways, and inference providers represented in the catalog.

List providers

GET/v1/providersAuthentication: Optional
cURL
curl https://api.use-allm.com/v1/providers \
  -H "Accept: application/json" \
  -H "Authorization: Bearer $ALLM_API_KEY"
TypeScript
const providers = await allm.providers.list();
console.log(providers.data[0].name);
JSON · 200
{
  "data": [
    {
      "id": "openai",
      "name": "OpenAI",
      "kind": "direct",
      "website": "https://openai.com",
      "tier": "P0",
      "deployment_count": 38
    }
  ]
}

Retrieve a provider

GET/v1/providers/{providerId}Authentication: Optional
providerId
stringrequired
Provider slug, for example openai or aws-bedrock.
cURL
curl https://api.use-allm.com/v1/providers/openai \
  -H "Authorization: Bearer $ALLM_API_KEY"

The response is a data envelope containing the provider and its current deployments.

Provider object

id
stringrequired
Stable provider slug.
name
stringrequired
Display name.
kind
enumrequired
direct, cloud, gateway, or inference_cloud.
website
urirequired
Provider website.
tier
stringrequired
ALLM catalog coverage priority.
deployment_count
integer
Number of current deployments; returned by list.

Errors

StatusCodeWhen it happens
404PROVIDER_NOT_FOUNDNo provider matches the requested provider ID.
429RATE_LIMIT_EXCEEDEDThe request quota has been exceeded.

Response metadata

Every successful response includes x-allm-catalog-release, x-request-id, and an ETag. Store the request ID in logs and the catalog release beside any persisted decision.