Update an LLM

Updates an existing LLM configuration including display information, endpoint configuration, model parameters, credentials, and labels. All fields are optional - only specified fields will be updated.

IMPORTANT: providerType is IMMUTABLE after creation and cannot be changed. Requires UPDATE_LLM_OWN permission for LLMs you own (or UPDATE_LLM_ANY for admin users).

Authorization

x-api-key<token>

In: header

Path Parameters

idstring

The unique identifier of the LLM to update

Request Body

LLM update details

displayName?string | null

Update display name

Default"Updated GPT-4 Turbo"

Lengthlength <= 255

description?string | null

Update description

Default"Updated OpenAI's GPT-4 Turbo model for enhanced chat completions"

endpointUrl?string | null

Update endpoint base URL (OpenAI-compatible base, typically ends with /v1)

Default"https://api.openai.com/v1"

apiPath?string | null

Update API path

Default"/chat/completions"

modelIdentifier?string | null

Update model identifier (cannot be empty)

Default"gpt-4-turbo-preview"

supportedModalities?array<Modality> | null

Update supported modalities (if array contains ≥1 elements, replaces stored set; if empty or omitted, no change)

Default["TEXT"]

credentials?ApiKey (CREDENTIAL_KIND_API_KEY) | GcpAdc (CREDENTIAL_KIND_GCP_ADC) | None (omit this field)

Update credentials

Default{"kind":"CREDENTIAL_KIND_API_KEY","apiKey":{"inlineSecret":"sk-rotated-llm-key"}}

Structured credential payload describing how GoodMem should authenticate with an upstream provider.

kindstring

Credential strategy — fixed to CREDENTIAL_KIND_API_KEY for this variant

Default"CREDENTIAL_KIND_API_KEY"

apiKeyApiKeyAuth

Configuration when kind is CREDENTIAL_KIND_API_KEY

Default

{"inlineSecret":"sk-1234567890abcdef","secretRef":{"uri":"vault://path/to/secret"},"headerName":"Authorization","prefix":"Bearer "}

labels?object | null

Optional annotations to aid operators (e.g., "owner=vertex")

Propertiesproperties <= 20

Empty Object

Structured credential payload describing how GoodMem should authenticate with an upstream provider.

kindstring

Credential strategy — fixed to CREDENTIAL_KIND_GCP_ADC for this variant

Default"CREDENTIAL_KIND_GCP_ADC"

gcpAdcGcpAdcAuth

Configuration when kind is CREDENTIAL_KIND_GCP_ADC

Default{"scopes":["https://www.googleapis.com/auth/cloud-platform"],"quotaProjectId":"my-quota-project"}

labels?object | null

Optional annotations to aid operators (e.g., "owner=vertex")

Propertiesproperties <= 20

Empty Object

version?string | null

Update version information

Default"2.0.1"

monitoringEndpoint?string | null

Update monitoring endpoint URL

Default"https://monitoring.company.com/llms/status"

capabilities?LLMCapabilities | null

Update LLM capabilities (replaces entire capability set; clients MUST send all flags)

Default

{"supportsChat":true,"supportsCompletion":true,"supportsFunctionCalling":true,"supportsSystemMessages":true,"supportsStreaming":true,"supportsSamplingParameters":true}

defaultSamplingParams?LLMSamplingParams | null

Update default sampling parameters

Default

{"maxTokens":2048,"temperature":0.7,"topP":0.9,"topK":50,"frequencyPenalty":0,"presencePenalty":0,"stopSequences":["\n\n","END"]}

maxContextLength?integer | null

Update maximum context window size in tokens

Default32768

Formatint32

clientConfig?object | null

Update provider-specific client configuration (replaces entire config; no merging)

Empty Object

replaceLabels?object | null

Replace all existing labels with this set. Empty map clears all labels. Cannot be used with mergeLabels.

Default{"environment":"production","team":"ml-platform"}

Empty Object

mergeLabels?object | null

Merge with existing labels: upserts with overwrite. Labels not mentioned are preserved. Cannot be used with replaceLabels.

Default{"cost-center":"ai-infrastructure"}

Empty Object

Response Body

curl -X PUT "http://localhost:8080/v1/llms/550e8400-e29b-41d4-a716-446655440000" \
  -H "Content-Type: application/json" \
  -d '{
    "displayName": "Updated GPT-4 Turbo",
    "description": "Updated OpenAI GPT-4 Turbo with enhanced configuration for production use",
    "endpointUrl": "https://api.openai.com/v1",
    "apiPath": "/chat/completions",
    "modelIdentifier": "gpt-4-turbo-preview",
    "supportedModalities": [
      "TEXT"
    ],
    "credentials": {
      "apiKey": {
        "inlineSecret": "sk-updated-api-key-here",
        "secretRef": {
          "uri": "vault://path/to/secret"
        },
        "headerName": "Authorization",
        "prefix": "Bearer "
      },
      "kind": "CREDENTIAL_KIND_API_KEY"
    },
    "version": "2.0.1",
    "monitoringEndpoint": "https://monitoring.company.com/llms/status",
    "capabilities": {
      "supportsChat": true,
      "supportsCompletion": true,
      "supportsFunctionCalling": true,
      "supportsSystemMessages": true,
      "supportsStreaming": true,
      "supportsSamplingParameters": true
    },
    "defaultSamplingParams": {
      "maxTokens": 2048,
      "temperature": 0.7,
      "topP": 0.9,
      "topK": 50,
      "frequencyPenalty": 0,
      "presencePenalty": 0,
      "stopSequences": [
        "\n\n",
        "END"
      ]
    },
    "maxContextLength": 32768,
    "replaceLabels": {
      "environment": "production",
      "team": "ml-platform",
      "cost-center": "ai-infrastructure"
    },
    "mergeLabels": {
      "cost-center": "ai-infrastructure"
    }
  }'

curl -X PUT "http://localhost:8080/v1/llms/550e8400-e29b-41d4-a716-446655440000" \  -H "Content-Type: application/json" \  -d '{    "displayName": "Updated GPT-4 Turbo",    "description": "Updated OpenAI GPT-4 Turbo with enhanced configuration for production use",    "endpointUrl": "https://api.openai.com/v1",    "apiPath": "/chat/completions",    "modelIdentifier": "gpt-4-turbo-preview",    "supportedModalities": [      "TEXT"    ],    "credentials": {      "apiKey": {        "inlineSecret": "sk-updated-api-key-here",        "secretRef": {          "uri": "vault://path/to/secret"        },        "headerName": "Authorization",        "prefix": "Bearer "      },      "kind": "CREDENTIAL_KIND_API_KEY"    },    "version": "2.0.1",    "monitoringEndpoint": "https://monitoring.company.com/llms/status",    "capabilities": {      "supportsChat": true,      "supportsCompletion": true,      "supportsFunctionCalling": true,      "supportsSystemMessages": true,      "supportsStreaming": true,      "supportsSamplingParameters": true    },    "defaultSamplingParams": {      "maxTokens": 2048,      "temperature": 0.7,      "topP": 0.9,      "topK": 50,      "frequencyPenalty": 0,      "presencePenalty": 0,      "stopSequences": [        "\n\n",        "END"      ]    },    "maxContextLength": 32768,    "replaceLabels": {      "environment": "production",      "team": "ml-platform",      "cost-center": "ai-infrastructure"    },    "mergeLabels": {      "cost-center": "ai-infrastructure"    }  }'

{
  "llmId": "550e8400-e29b-41d4-a716-446655440000",
  "displayName": "GPT-4 Turbo",
  "description": "OpenAI's GPT-4 Turbo model for chat completions",
  "providerType": "OPENAI",
  "endpointUrl": "https://api.openai.com/v1",
  "apiPath": "/chat/completions",
  "modelIdentifier": "gpt-4-turbo-preview",
  "supportedModalities": [
    "TEXT"
  ],
  "credentials": {
    "apiKey": {
      "inlineSecret": "sk-1234567890abcdef",
      "secretRef": {
        "uri": "vault://path/to/secret"
      },
      "headerName": "Authorization",
      "prefix": "Bearer "
    },
    "gcpAdc": {
      "scopes": [
        "https://www.googleapis.com/auth/cloud-platform"
      ],
      "quotaProjectId": "my-quota-project"
    }
  },
  "labels": {
    "environment": "production",
    "team": "ai"
  },
  "version": "1.0.0",
  "monitoringEndpoint": "https://monitoring.example.com/llms/status",
  "capabilities": {
    "supportsChat": true,
    "supportsCompletion": true,
    "supportsFunctionCalling": true,
    "supportsSystemMessages": true,
    "supportsStreaming": true,
    "supportsSamplingParameters": true
  },
  "defaultSamplingParams": {
    "maxTokens": 2048,
    "temperature": 0.7,
    "topP": 0.9,
    "topK": 50,
    "frequencyPenalty": 0,
    "presencePenalty": 0,
    "stopSequences": [
      "\n\n",
      "END"
    ]
  },
  "maxContextLength": 32768,
  "clientConfig": {
    "property1": {},
    "property2": {}
  },
  "ownerId": "550e8400-e29b-41d4-a716-446655440000",
  "createdAt": 1617293472000,
  "updatedAt": 1617293472000,
  "createdById": "550e8400-e29b-41d4-a716-446655440000",
  "updatedById": "550e8400-e29b-41d4-a716-446655440000"
}

Empty

Update an LLM

Authorization

Path Parameters

Request Body

Response Body

200

400

401

403

404

409