List the models available at one provider entry

curl --request GET \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "provider": "<string>",
  "index": 123,
  "entry": {
    "endpoint": "<string>",
    "resource": "<string>",
    "region": "<string>",
    "host": "<string>",
    "carbon_region": "<string>"
  },
  "total": 123,
  "models": [
    {
      "id": "<string>",
      "declared": true,
      "declared_as": "<string>",
      "registered": true
    }
  ]
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Models

List the models available at one provider entry

Calls the provider’s own model listing for ONE entry of the saved gateway configuration (OpenAI and OpenAI-compatible /models, Azure OpenAI deployments, Anthropic /v1/models, Vertex Model Garden publisher models, Bedrock foundation models and inference profiles). Credentials stay server-side. Each model keeps the provider’s own fields as-is, plus a standardized id (the value to declare in the entry), declared and registered. Requires write access to models.

GET

providers

{type}

{index}

models

List the models available at one provider entry

curl --request GET \
  --url https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models \
  --header 'Authorization: Bearer <token>'

const options = {method: 'GET', headers: {Authorization: 'Bearer <token>'}};

fetch('https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

import requests

url = "https://{host}/v2/workspaces/slug:llm-gateway/webhooks/v1/providers/{type}/{index}/models"

headers = {"Authorization": "Bearer <token>"}

response = requests.get(url, headers=headers)

print(response.text)

{
  "provider": "<string>",
  "index": 123,
  "entry": {
    "endpoint": "<string>",
    "resource": "<string>",
    "region": "<string>",
    "host": "<string>",
    "carbon_region": "<string>"
  },
  "total": 123,
  "models": [
    {
      "id": "<string>",
      "declared": true,
      "declared_as": "<string>",
      "registered": true
    }
  ]
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

{
  "error": "<string>",
  "message": "<string>",
  "code": "<string>",
  "details": {},
  "status": 123,
  "retryAfter": 123,
  "provider": "<string>",
  "model": "<string>",
  "provider_error_type": "<string>"
}

Authorizations

Authorization

string

header

required

User-bound credential carrying an identity: either a session JWT or a user access token (at:*) generated from the user settings UI. Send as Authorization: Bearer <token>. Org API keys (iak_*) are not accepted here - they carry no user identity. Use the x-prismeai-api-key header instead (see OrgApiKeyAuth).

Path Parameters

type

enum<string>

required

Provider type, a key of the gateway providers configuration.

Available options:

openai,

azure_openai,

openailike,

anthropic,

vertex,

bedrock

index

integer

required

Position of the entry in providers.<type> (providers.azure_openai.resources for Azure); 0 for the single-object providers.

Required range: x >= 0

Response

Models available at the provider entry.

provider

string

index

integer

entry

object

Non-secret identity of the entry, to check it is the expected one.

Hide child attributes

entry.endpoint

string | null

entry.resource

string | null

entry.region

string | null

entry.host

string | null

entry.carbon_region

string | null

total

integer

models

object[]

Hide child attributes

models.id

string

required

Value to declare in the entry's model list (Azure deployment name, Bedrock model or inference profile id, Vertex resource path…).

models.declared

boolean

Already listed in the entry, directly or through a model_aliases alias.

models.declared_as

string | null

The public id the entry declares for this model (the id itself, or its alias).

models.registered

boolean

Already registered in the models collection.

Introduction

Platform API

Agent Creator API

LLM Gateway API

Governance API

Knowledges API

Collections API

List the models available at one provider entry

Authorizations

Path Parameters

Response