Skip to main content
POST
Create a response

Authorizations

Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your auth token.

Body

application/json

Response creation parameters

model
string
required

The model to use for generating the response.

  • nimbus-001: Fast general question answering model. Requires knowledge_base. Default temperature: 0.7.
  • nimbus-002-preview: Light reasoning model capable of multi-step reasoning, cross-video synthesis, and structured entity data. Requires knowledge_base. Supports entity_collections in the knowledge base. Default temperature: 1.

Metadata collections (collection_type: 'metadata') in the knowledge base are only supported by nimbus-002-preview — its agent retrieves them at file granularity; nimbus-001 rejects them (400).

Minimum string length: 1
Example:

"nimbus-001"

input
required

The input for the response. Can be a simple string or an array of messages.

instructions
string

System instructions to guide the model's behavior (maps to developer/system message)

temperature
number

Sampling temperature for the model. Defaults to 0.7 for nimbus-001 and 1 for nimbus-002-preview.

Required range: 0 <= x <= 2
knowledge_base
object

Knowledge base configuration. Required for nimbus-001 and nimbus-002-preview.

include
enum<string>[]

Additional data to include in the response annotations

Available options:
cloudglue_citations.media_descriptions
tools
object[]

Tool definitions for function calling.

max_output_tokens
integer

Maximum number of output tokens.

Required range: 1 <= x <= 128000
background
boolean

Set to true to process the response in the background. When true, the response is returned immediately with status 'in_progress'.

stream
boolean

Stream response via SSE. Mutually exclusive with background.

Response

Response created successfully

id
string<uuid>

Unique identifier for the response

object
enum<string>

Object type identifier

Available options:
response
status
enum<string>

Current status of the response

Available options:
in_progress,
completed,
failed,
cancelled
created_at
integer

Unix timestamp of when the response was created

model
string

The model used for the response

instructions
string | null

The system instructions used

output
object[] | null

The generated output messages

usage
object | null

Token usage statistics for the response

error
object | null

Error details when the response status is 'failed'