v3

latestOpenAPI 3.1.02026-07-311,4541,5202.3 MB

platformApi

Api Response Format Presets List

GET/POST /api/response-format-presets/ — list and create presets.

Response-format presets intentionally form a separate resource from LLMPreset. LLM presets snapshot the complete model setup, including model, tools, and variable values; storing schemas there would couple a reusable response format to unrelated execution settings and risk applying those settings when a schema is loaded.

This endpoint instead provides a project-shared schema library. Loading a preset only returns content for the client to copy into its draft editor; it does not mutate a prompt or create a live link to the preset. Clients can POST an edited draft as a new preset, leaving the source unchanged.

get/api/response-format-presets/

Query parameters

pageinteger

A page number within the paginated result set.

page_sizeinteger

Number of results to return per page.

Headers

Authorizationstring required

JWT access token or Respan API key

Response

countinteger required

nextstring uri nullable

previousstring uri nullable

total_countinteger

current_filtersFilterParamDictPydantic

Pydantic model for FilterParamDict. A dictionary that maps metric names to their filter parameters.

Each key is a metric name (str), and each value can be:

A single MetricFilterParamPydantic (one condition)
A List[MetricFilterParamPydantic] (multiple conditions for same metric)
A FilterBundlePydantic (nested filter bundle with connector)

Note: Uses extra="allow" for dynamic metric name fields. The pydantic_extra annotation tells Pydantic what types to expect for extra fields, and generates typed additionalProperties in JSON Schema.

filters_dataPaginatedResponseFormatPresetListListFiltersData