> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lighton.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# List catalogued provider models

> Return the known models for a SaaS provider, to populate the model picker in the custom-model create flow. Derived from LiteLLM's published model cost map, refreshed daily, and filtered to models that are registrable as custom models and not past their published deprecation date. The catalogue is a convenience, not a constraint: create accepts any litellm_model string, so a model absent from the list can still be registered by entering it directly. An empty list is a valid response — the provider may publish no models of the requested type, or the catalogue may be briefly unavailable. Requires company admin role.



## OpenAPI

````yaml /api-reference/openapi-v3-company.yaml get /api/v3/company/model-catalog
openapi: 3.1.0
info:
  title: LightOn API
  version: 3.15.0 (v3-company)
  description: >-
    LightOn gives you an API to search, parse, and ingest documents at scale.
    Build knowledge-retrieval pipelines without managing vector databases or OCR
    models.
servers:
  - url: https://paradigm.lighton.ai
security: []
tags:
  - name: Models
    description: Operations about AI models
  - name: Workspaces
    description: Operations about workspaces
  - name: Users
    description: Operations about users
  - name: User Groups
    description: Operations about user groups
  - name: Companies
    description: Operations about companies
paths:
  /api/v3/company/model-catalog:
    get:
      tags:
        - Models
      summary: List catalogued provider models
      description: >-
        Return the known models for a SaaS provider, to populate the model
        picker in the custom-model create flow. Derived from LiteLLM's published
        model cost map, refreshed daily, and filtered to models that are
        registrable as custom models and not past their published deprecation
        date. The catalogue is a convenience, not a constraint: create accepts
        any litellm_model string, so a model absent from the list can still be
        registered by entering it directly. An empty list is a valid response —
        the provider may publish no models of the requested type, or the
        catalogue may be briefly unavailable. Requires company admin role.
      operationId: api_v3_company_model_catalog_list
      parameters:
        - in: query
          name: model_type
          schema:
            type: string
            enum:
              - Embedding Model
              - Large Language Model
              - Multi-Vector Model
              - Vision Language Model
          description: >-
            Narrow the catalogue to a single model type. Omit to return every
            entry.
        - in: query
          name: provider
          schema:
            type: string
            enum:
              - anthropic
              - gemini
              - mistral
              - openai
          description: Provider whose catalogue to return.
          required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                type: array
                items:
                  $ref: '#/components/schemas/ProviderCatalogEntryResponse'
              examples:
                AnthropicLanguageModels:
                  value:
                    - - litellm_model: anthropic/claude-opus-5
                        label: claude-opus-5
                        model_type: Large Language Model
                        max_input_tokens: 1000000
                        required_temperature: 1
                        max_temperature: 1
                      - litellm_model: anthropic/claude-haiku-4-5
                        label: claude-haiku-4-5
                        model_type: Large Language Model
                        max_input_tokens: 200000
                        required_temperature: null
                        max_temperature: 1
                  summary: Anthropic language models
          description: ''
        '403':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/APIV3ErrorResponse'
              examples:
                Forbidden:
                  value:
                    id: null
                    code: 403
                    error: insufficient_permissions
                    detail: Admin access required.
                    doc_url: >-
                      https://developers.lighton.ai/errors#insufficient_permissions
          description: >-
            Admin access required. Only company admins and superadmins can write
            custom models.
        '422':
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/APIV3ErrorResponse'
              examples:
                UnknownProvider:
                  value:
                    id: null
                    code: 422
                    error: validation_error
                    detail: One or more fields failed validation.
                    doc_url: https://developers.lighton.ai/errors#validation_error
                    fields:
                      provider:
                        - error: invalid_choice
                          detail: >-
                            Unknown provider 'cohere'. Expected one of:
                            anthropic, gemini, mistral, openai.
                  summary: Unknown provider
                MissingProvider:
                  value:
                    id: null
                    code: 422
                    error: validation_error
                    detail: One or more fields failed validation.
                    doc_url: https://developers.lighton.ai/errors#validation_error
                    fields:
                      provider:
                        - error: required
                          detail: This query parameter is required.
                  summary: Missing provider
          description: >-
            The provider is missing, or the provider or model type is not
            recognised.
        '503':
          description: >-
            API is under maintenance. Check `GET /api/v3/system/status` for
            active periods and retry.
          content:
            application/json:
              schema:
                $ref: '#/components/schemas/ServiceMaintenance503'
      security:
        - bearerAuth: []
components:
  schemas:
    ProviderCatalogEntryResponse:
      type: object
      properties:
        litellm_model:
          type: string
          description: >-
            LiteLLM model string to submit as `litellm_model` when creating the
            custom model.
        label:
          type: string
          description: The provider's own model identifier, for display in a picker.
        model_type:
          type: string
          description: Model type this entry can be registered as.
        max_input_tokens:
          type:
            - integer
            - 'null'
          description: Context window in tokens, when the provider publishes one.
        required_temperature:
          type:
            - number
            - 'null'
          format: double
          description: >-
            The only temperature this model accepts, when it accepts exactly
            one. Offer it as the temperature for this model; null means any
            value within the range is fine.
        max_temperature:
          type:
            - number
            - 'null'
          format: double
          description: >-
            Highest temperature this provider accepts. Null when the provider
            publishes no bound.
      required:
        - label
        - litellm_model
        - model_type
    APIV3ErrorResponse:
      type: object
      properties:
        id:
          type:
            - string
            - 'null'
          description: >-
            Job/resource id when one already exists (useful for async error
            diagnosis); null otherwise.
        code:
          type: integer
          description: HTTP status code
        error:
          type: string
          description: Error code used by the UI as a translation key
        detail:
          type: string
          description: Human-readable error message for developers
        doc_url:
          type: string
          description: Link to the error-code documentation page
      required:
        - code
        - detail
        - doc_url
        - error
        - id
    ServiceMaintenance503:
      type: object
      description: >-
        Returned by the maintenance middleware when the requested endpoint is
        blocked.
      required:
        - detail
        - error
        - mode
      properties:
        detail:
          type: string
          example: System is under maintenance.
        error:
          type: string
          example: service_maintenance
        mode:
          type: string
          enum:
            - full_shutdown
            - warning_banner
          description: >-
            `full_shutdown` blocks all traffic; `warning_banner` also blocks and
            shows a dismissible toast.
        reason:
          type: string
          description: Operator-supplied maintenance reason, if any.
        started_at:
          type: string
          format: date-time
        endpoint_category_names:
          type: array
          items:
            type: string
          description: >-
            Non-empty only for category-scoped periods. Empty means all
            endpoints are affected.
  securitySchemes:
    bearerAuth:
      type: http
      scheme: bearer
      description: >-
        Bearer authentication header of the form `Bearer <token>`, where
        `<token>` is your auth token.

````