Get AI Gateway Settings

Endpoint

GET /apiops/settings/ai-gateway

Authentication

Requires a Personal API Access Token with admin privileges.

Header

Authorization: Bearer YOUR_TOKEN

Request

Headers

Header	Value	Required
Authorization	Bearer {token}	Yes

Path Parameters

None.

Query Parameters

None.

Response

Success Response (200 OK)

The settings are returned as a single object inside resultList. Entity getters are null-safe, so the response always carries the effective value: any field that has never been set is returned with its platform default rather than null.

{
  "status": "SUCCESS",
  "resultList": [
    {
      "defaultConnectTimeoutSeconds": 10,
      "defaultStreamTimeoutSeconds": 120,
      "defaultRetryCount": 0,
      "maxAiRequestBodyBytes": 10485760,
      "maxAiBinaryRequestBodyBytes": 26214400,
      "maxAiBinaryResponseBodyBytes": 26214400,
      "maxToolTurns": 5,
      "defaultConnectionPoolSize": 64,
      "defaultIdleConnectionTimeoutSeconds": 4
    }
  ],
  "resultCount": 1
}

Response Fields

Field	Type	Description
status	string	Response status: SUCCESS or FAILURE
resultList	array	List containing the single settings object
resultCount	integer	Always 1 for this singleton resource

Settings Object Fields

Field	Type	Default	Description
defaultConnectTimeoutSeconds	integer	10	Connect timeout to the LLM provider, in seconds (1-300)
defaultStreamTimeoutSeconds	integer	120	Overall SSE stream timeout, in seconds (1-3600)
defaultRetryCount	integer	0	Retry attempts on provider error (0-10); 0 = no retry
maxAiRequestBodyBytes	integer	10485760	Max JSON AI request body size in bytes (10 MB default)
maxAiBinaryRequestBodyBytes	integer	26214400	Max binary/multipart AI request body size in bytes (25 MB default, e.g. audio transcription uploads)
maxAiBinaryResponseBodyBytes	integer	26214400	Max binary AI response body size in bytes (25 MB default, e.g. TTS/image-gen output)
maxToolTurns	integer	5	Ceiling on chained agentic tool-call turns; <= 0 disables the loop (passthrough)
defaultConnectionPoolSize	integer	64	Idle connections kept open for reuse for each LLM provider of an AI proxy whose connection pool type is GENERAL (1-1000)
defaultIdleConnectionTimeoutSeconds	integer	4	Seconds an idle connection is kept for reuse in a GENERAL pool (1-3600)

EnumStatus

• SUCCESS - Operation successful
• FAILURE - Operation failed

Error Response (400 Bad Request)

Returned when the caller is authenticated but lacks the ADMIN role.

{
  "status": "FAILURE",
  "resultMessage": "Unauthorized! Only users with ADMIN role can access this resource!"
}

Error Response (401 Unauthorized)

{
  "status": "FAILURE",
  "resultMessage": "Token is not valid!"
}

Causes

• Missing or invalid Authorization header
• Token expired or revoked
• Invalid token format

cURL Example

curl -X GET \
  "https://demo.apinizer.com/apiops/settings/ai-gateway" \
  -H "Authorization: Bearer YOUR_TOKEN"

Notes and Warnings

• Admin Only:
  • Only sysAdmin users (or users with the ADMIN role) can read AI Gateway settings
  • A project-scoped AI_DEVELOPMENT token is not sufficient
• Singleton:
  • A single document governs the entire platform; resultCount is always 1
  • If no document exists yet, defaults are returned (a new document is not persisted on read)
• Effective Values:
  • Getters are null-safe, so the response always reflects the effective value in force (platform default when a field was never explicitly set)
• No Secret Fields:
  • This settings document carries no secret (@SecretData) fields, so no values are masked

Related Documentation

• Update AI Gateway Settings - Update these settings
• AI Gateway Settings API - Resource overview
• Authentication Guide - How to obtain and use API tokens