Update an integration

Partially update an integration. type is immutable (and, for LLM, config.provider). At least one field must be provided.

Payload Requirements

• type is required (it selects the per-type PATCH shape) and is immutable: it must match the stored integration’s type, otherwise the request is rejected with 422 (change category by delete + recreate).
• At least one updatable field (name, description, scopings, config) must be provided in addition to type.
• Scalar fields deep-merge: omit = keep, explicit null = clear (for nullable fields).
• Collection fields (scopings, config.headers) replace the existing values when provided.
• For type: EVALUATOR, config.headers accepts a string map (replace), null (clear), or may be omitted (keep).
• type: EVALUATOR requires the remote evaluators feature to be enabled.

Valid example (type: EVALUATOR)

{
  "type": "EVALUATOR",
  "config": {
    "endpoint": "https://eval.example.com/v2/evaluate"
  }
}

Invalid example (type mismatch)

{
  "type": "AGENT"
}

This endpoint is in alpha, read more here.

PATCH /v2/integrations/{integration_id}

cURL

update_llm

curl --request PATCH \ --url https://api.arize.com/v2/integrations/{integration_id} \ --header 'Authorization: Bearer <token>' \ --header 'Content-Type: application/json' \ --data ' { "type": "LLM", "name": "Updated OpenAI", "config": { "is_function_calling_enabled": true } } '

200

llm_integration

{ "id": "TGxtSW50ZWdyYXRpb246MTI6YUJjRA==", "type": "LLM", "name": "Production OpenAI", "scopings": [ { "organization_id": null, "space_id": null } ], "created_at": "2026-02-13T21:27:19.055Z", "updated_at": "2026-02-13T21:27:19.279Z", "created_by_user_id": "VXNlcjoxOm5OYkM=", "config": { "provider": "OPEN_AI", "has_api_key": true, "is_function_calling_enabled": true } }

Authorizations

Authorization · string · header · required

Most Arize AI endpoints require authentication. For those endpoints that require authentication, include your API key in the request header using the format

Path Parameters

integration_id · string · required

The unique integration identifier. A universally unique identifier (base64-encoded opaque string).

Example:

"RW50aXR5OjEyMzQ1"

Body

application/json

Partially update an integration. The body is discriminated by type. Omitted fields are left unchanged.

Payload Requirements

• type is required (it selects the per-type PATCH shape) and is immutable: it must match the stored integration's type, otherwise the request is rejected with 422 (change category by delete + recreate).
• At least one updatable field (name, scopings, config, or — for AGENT and EVALUATOR — description) must be provided in addition to type. description is not a valid field for type: LLM and is rejected.
• For LLM, config.provider is immutable, and config-field applicability is provider-specific (enforced with 422) — see the per-field docs on UpdateLlmConfig.
• Envelope and config scalar fields deep-merge: omit = keep, explicit null = clear (for nullable fields).
• Collections (scopings, config.model_names, config.headers, config.request_presets) replace the existing values when provided.
• For type: EVALUATOR, config.headers accepts a string map (replace), null (clear), or may be omitted (keep).

Valid example

{
  "type": "LLM",
  "name": "Updated OpenAI",
  "config": { "is_function_calling_enabled": true }
}

Invalid example (empty body)

{}

Option 1

Option 2

Option 3

Partial update of an integration, discriminated by type (immutable). The type field selects the per-type PATCH shape. Provide at least one updatable field in addition to type.

type · enum<string> · required

Discriminator. Immutable; must match the integration's type.

Available options: LLM

name · string

New integration name.

scopings · object[]

Replaces the existing scoping rules.

Show child attributes

config · object

Partial LLM config for PATCH. provider is immutable; if present it must match the stored value. Invalid provider/field combinations return 422.

Provider-specific fields:

• api_key, is_function_calling_enabled: all except AWS_BEDROCK, VERTEX_AI
• auth: AWS_BEDROCK only
• base_url: ANTHROPIC, CUSTOM, LITELLM, NVIDIA_NIM
• headers: CUSTOM, LITELLM, NVIDIA_NIM
• is_default_models_enabled: AWS_BEDROCK, CUSTOM, FIREWORKS, NVIDIA_NIM
• model_names: AWS_BEDROCK, CUSTOM, FIREWORKS, LITELLM, NVIDIA_NIM
• project_id, location, project_access_label: VERTEX_AI only

Show child attributes

Response

200

application/json

An integration object.

Option 1

Option 2

Option 3

A polymorphic integration resource. The type field selects the config shape; for LLM, config.provider selects the per-provider config.

id · string · required

The unique identifier for the integration.

type · enum<string> · required

Discriminator identifying an LLM integration.

Available options: LLM

name · string · required

The integration name. Unique per (account, type).

scopings · object[] · required

Visibility scoping rules. Account-wide when empty.

Show child attributes

created_at · string<date-time> · required

When the integration was created.

updated_at · string<date-time> · required

When the integration was last updated.

created_by_user_id · string · required

Unique identifier of the user who created the integration.

config · object · required

Per-provider LLM config, discriminated by provider.

Option 1

Option 2

Option 3

Option 4

Option 5

Option 6

Option 7

Option 8

Option 9

Show child attributes