Skip to main content
POST
Create a large language model together with its credentials and Gateway Config Set (EXPERIMENTAL)

Authorizations

X-API-Key
string
header
required

Supply the API Key in the HTTP-Header

Headers

Accept
enum<string>

The Accept header specifies the media type that the client expects in the response. Available options: application/json, application/hal+json, application/xml, text/xml, text/csv. The default value is application/json.

Available options:
application/json,
application/hal+json,
application/xml,
text/xml,
text/csv

Body

application/json
largeLanguageModel
object
required

The large language model half of the unified LLM configuration request. Same field set as the plain largelanguagemodels resource, minus connectionId (always derived server-side from credentials) and every server-managed field (configSetId, isInPlatformLlm, useCases, ...).

credentials
object
required

Credentials for the large language model being configured. mode is explicit rather than inferred from the presence of referenceId.

resourceLevel
enum<string>
default:project

General scope of the resource.

Available options:
organisation,
project
projectId
string
Required string length: 24
Pattern: ^[a-z0-9]{24}$

Response

Returns the created large language model, a summary of its credentials (never the field values), and the Config Set sync outcome.

largeLanguageModel
object

The IEntityMeta defines meta information every entity within the system has. These are dates when a resource was created and modified as well as information about the user who initially created a resource and who modified it the last time.

credentials
object

Never includes fields — credential values are never echoed back by this route.

configSet
object

Whether a Gateway Config Set was created/updated for this large language model, or why it was skipped.

Last modified on September 16, 2026