curl --request PUT \
  --url https://api.example.com/v3/llm-gateway/providers/{provider} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "provider": "openai",
  "models": [
    {
      "name": "gpt-4"
    },
    {
      "name": "gpt-3.5-turbo"
    },
    {
      "name": "gpt-4o-mini"
    }
  ]
}
'

{
  "api": "v3",
  "data": {
    "id": 1,
    "uuid": "550e8400-e29b-41d4-a716-446655440000",
    "provider": "OpenAI",
    "credentials": [
      {
        "name": "Production Key",
        "uuid": "550e8400-e29b-41d4-a716-446655440004",
        "credential_type": "api_key"
      },
      {
        "name": "Development Key",
        "uuid": "550e8400-e29b-41d4-a716-446655440005",
        "credential_type": "api_key"
      }
    ],
    "models": [
      {
        "name": "gpt-4",
        "uuid": "550e8400-e29b-41d4-a716-446655440008",
        "state": "active"
      },
      {
        "name": "gpt-3.5-turbo",
        "uuid": "550e8400-e29b-41d4-a716-446655440009",
        "state": "deprecating",
        "retire_at": "2026-12-11"
      },
      {
        "name": "gpt-4o-mini",
        "uuid": "550e8400-e29b-41d4-a716-446655440010",
        "state": "active"
      }
    ],
    "created_at": "2025-01-08T00:00:00Z",
    "updated_at": "2025-01-08T13:00:00Z",
    "created_by": {
      "id": "550e8400-e29b-41d4-a716-446655440002",
      "full_name": "Joe Schmoe",
      "email": "joe_schmoe@email.com"
    }
  }
}

LLM Gateway

Update LLM provider

Update an existing LLM provider’s models and credentials. This is a replace operation - pass the complete desired state. For credentials: include existing ones (name/uuid) to keep them, add new ones (name/credential_config) to create them, omit any to remove them. For models: pass the complete list of desired models. Any fields not included will be removed. The provider in the body must match the one in the path. If the update removes models or credentials that evaluator rules use, it is refused with a 409 unless acknowledge_usage=true is sent; those rules then fail when they next run. Call GET /llm-gateway/providers/{provider}/usage first to warn the user.

PUT

/

v3

/

llm-gateway

/

providers

/

{provider}

curl --request PUT \
  --url https://api.example.com/v3/llm-gateway/providers/{provider} \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "provider": "openai",
  "models": [
    {
      "name": "gpt-4"
    },
    {
      "name": "gpt-3.5-turbo"
    },
    {
      "name": "gpt-4o-mini"
    }
  ]
}
'

{
  "api": "v3",
  "data": {
    "id": 1,
    "uuid": "550e8400-e29b-41d4-a716-446655440000",
    "provider": "OpenAI",
    "credentials": [
      {
        "name": "Production Key",
        "uuid": "550e8400-e29b-41d4-a716-446655440004",
        "credential_type": "api_key"
      },
      {
        "name": "Development Key",
        "uuid": "550e8400-e29b-41d4-a716-446655440005",
        "credential_type": "api_key"
      }
    ],
    "models": [
      {
        "name": "gpt-4",
        "uuid": "550e8400-e29b-41d4-a716-446655440008",
        "state": "active"
      },
      {
        "name": "gpt-3.5-turbo",
        "uuid": "550e8400-e29b-41d4-a716-446655440009",
        "state": "deprecating",
        "retire_at": "2026-12-11"
      },
      {
        "name": "gpt-4o-mini",
        "uuid": "550e8400-e29b-41d4-a716-446655440010",
        "state": "active"
      }
    ],
    "created_at": "2025-01-08T00:00:00Z",
    "updated_at": "2025-01-08T13:00:00Z",
    "created_by": {
      "id": "550e8400-e29b-41d4-a716-446655440002",
      "full_name": "Joe Schmoe",
      "email": "joe_schmoe@email.com"
    }
  }
}

Authorizations

Authorization

string

header

required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Path Parameters

provider

string

required

Name of the LLM provider (e.g., OpenAI, Anthropic)

Query Parameters

acknowledge_usage

boolean

default:false

Remove models or credentials even though evaluator rules use them. Those rules fail when they next run.

Body

application/json

Request body for updating an LLM provider. This is a replace operation where you specify the complete desired state. Omitted fields will be removed.

provider

string

required

Name of the LLM provider

api_base

string | null

Custom API base URL. Required for some providers (e.g., Databricks), optional for others (e.g., Bedrock VPC endpoints). Must use HTTPS.

Maximum string length: 512

models

Model Compact Request · object[]

Complete list of models to support. This replaces all existing models.

Show child attributes

credentials

Credential Update · object[]

Complete list of credentials. Include existing ones (name/uuid) to keep them, add new ones (name/credential_config) to create them. Omitted credentials will be removed.

Show child attributes

Response

LLM provider updated successfully

Response object for standard API responses.

api_version

enum<string>

default:3.0

API version.

Available options:

2.0,

3.0

kind

enum<string>

default:NORMAL

Type of response, indicating a normal response.

Available options:

NORMAL

data

object

Details of an LLM provider

Show child attributes