Skip to main content
POST
/
api
/
organizations
/
{orgId}
/
llm
Invoke LLM
curl --request POST \
  --url https://platform.kodexa.ai/api/organizations/{orgId}/llm \
  --header 'Content-Type: application/json' \
  --header 'x-api-key: <api-key>' \
  --data '
{
  "parameters": {},
  "prompt": "<string>",
  "promptRef": "<string>"
}
'
"<string>"

Authorizations

​
x-api-key
string
header
required

API key for authentication. Create one from the Kodexa platform UI under Settings > Access Tokens.

Path Parameters

​
orgId
string<uuid>
required

Unique identifier (UUID) of the organization.

Body

application/json

Request body for invoking the platform LLM. Supply either a promptRef (referencing a stored prompt template) or an inline prompt string.

​
modelType
enum<string>

Size of the model to use.

Available options:
SMALL,
LARGE
​
parameters
object

Key-value parameters for template rendering.

​
prompt
string

Inline prompt text. Mutually exclusive with promptRef.

​
promptRef
string

Reference to a stored prompt template (e.g., 'orgSlug/promptSlug' or 'promptSlug'). Mutually exclusive with prompt.

Response

LLM response text

The response is of type string.