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

# Import models from LiteLLM

> Bulk-imports a list of LiteLLM model definitions into the workspace model garden.

<Note>
  **Related guide**: AI Router guide. See the [AI Router guide](/docs/ai-gateway/using-the-router) for a walkthrough with examples.
</Note>


## OpenAPI

````yaml post /v2/models/litellm/import
openapi: 3.1.0
info:
  title: orq.ai API
  version: '2.0'
  description: orq.ai API documentation
servers:
  - url: https://my.orq.ai
security:
  - ApiKey: []
tags:
  - name: Chunking
    description: Split text into smaller chunks for retrieval and generation workflows.
  - name: File Systems
    description: >-
      Create and manage persistent file systems that agents and MCP clients read
      from and write to.
  - name: Knowledge Bases
    description: Create and manage knowledge bases used by agents and retrieval workflows.
  - name: Memory Stores
    description: Create and manage memory stores, memories, and memory documents.
  - name: Evals
    description: Run an evaluator against a conversation and its result
  - name: Logs
    description: >-
      OpenTelemetry log query API. Search, filter, aggregate, and facet log
      records ingested via OTLP.
  - name: Reporting
    description: >-
      GenAI reporting API over canonical analytics rollups. Accepts a metric
      name, time range, grain, group-by, and filters; returns a typed time
      series and optional totals.
  - name: Traces
    description: >-
      Query and inspect ingested trace data: search trace summaries, aggregate
      metrics, and read individual traces and their spans.
  - description: List models available through the AI Router.
    name: Models
  - name: Policies
  - name: Alerts
    description: >-
      Alerts evaluate a Reporting API metric on a fixed interval and fire
      notifications through notifiers when the value breaches a threshold. Each
      breach opens a trigger that tracks the incident until the value recovers.
  - name: Annotation Queues
    description: Annotation queues collect spans for human review.
  - name: API keys
    description: >-
      API keys authenticate programmatic access to the workspace. They expose
      opaque tokens, per-domain access grants, and budget and rate-limit
      constraints.
  - name: Audit Logs
    description: Audit logs record workspace entity changes and access-relevant events.
  - name: Budgets
    description: >-
      Budgets govern spend, token usage, and request rate across six scopes:
      workspace, project, identity, API key, provider, and model. Every
      applicable budget is enforced, and the most restrictive limit applies per
      dimension.
  - name: Files
    description: File upload and retrieval operations.
  - name: Guardrail Rules
    description: >-
      Guardrail Rules conditionally enforce evaluators and plugins for AI
      Gateway traffic. Rules may be scoped to a project or the whole workspace.
  - name: Hub
    description: Hub items are reusable templates available to a workspace.
  - name: Identities
    description: >-
      Identities represent end users from your system for usage and engagement
      tracking.
  - name: Management keys
    description: >-
      Management keys are workspace-scoped credentials that authenticate
      programmatic access to workspace administration surfaces (API keys,
      budgets). Unlike project-scoped API keys, a management key always operates
      at the workspace level.
  - name: MCP Gateway
    description: >-
      Register upstream MCP servers, discover and sync their tools, and assemble
      gateways that expose a curated tool surface to MCP clients.
  - name: Model Catalog
    description: >-
      Browse the orq.ai model catalog: every model orq offers, across every
      provider, with pricing, capabilities and benchmark data. List endpoints
      only return models that are not deprecated. This API is public, requires
      no authentication, and is rate limited to 120 requests per minute per IP.
      Responses carry a 5-minute cache-control max-age.
  - name: Notifiers
    description: Notifier destinations used to send delivery and workflow notifications.
  - name: Projects
    description: Projects organize resources within a workspace
  - name: Routing Rules
    description: >-
      Routing Rules conditionally select models and enforce request plugins for
      AI Gateway traffic. Rules are evaluated by ascending priority and may be
      scoped to a project or the whole workspace.
  - name: Threads
    description: Threads group related trace invocations and their aggregate usage
  - name: Skills
    description: >-
      Skills are modular instructions you can use to codify processes and
      conventions
  - name: Smart Routers
    description: >-
      Create and manage workspace Smart Routers. A Smart Router selects a model
      from an eligible pool for each request according to a quality, balanced,
      or cost profile.
  - name: Webhooks
    description: >-
      Create and manage webhooks that deliver workspace events to external HTTPS
      endpoints.
  - name: Workspaces
    description: >-
      A workspace is the tenant. Create is a user-session onboarding RPC; Get,
      List, and Update are the public management surface.
  - name: Workspace Security
    description: >-
      Workspace-level domain verification and IP allowlist controls. These
      operations are restricted to workspace administrators.
  - name: Workspace Settings
    description: >-
      Workspace-level settings managed with a workspace credential. A workspace
      is the tenant, so these settings are a singleton — there is nothing to
      create or delete, only read and update.
  - name: Responses
  - description: Run agents on a cron cadence. Minimum firing interval is 1 hour.
    name: Agent Schedules
  - name: Embeddings
  - name: Telemetry
    description: >-
      Unified query envelope for traces, metrics, and logs (ADR 0004). One
      request shape, one filter dialect, and one response shape per source,
      validated by a per-source registry.
externalDocs:
  url: https://docs.orq.ai
  description: orq.ai Documentation
paths:
  /v2/models/litellm/import:
    post:
      tags:
        - Models
      summary: Import models from LiteLLM
      description: >-
        Bulk-imports a list of LiteLLM model definitions into the workspace
        model garden.
      operationId: ModelLiteLLMImport
      requestBody:
        content:
          application/json:
            schema:
              items:
                $ref: '#/components/schemas/LiteLLMModel'
              type:
                - array
                - 'null'
        required: true
      responses:
        '200':
          content:
            application/json:
              schema:
                items:
                  $ref: '#/components/schemas/ModelDocument'
                type:
                  - array
                  - 'null'
          description: LiteLLM models imported successfully
        '400':
          description: Invalid request
        '401':
          description: Unauthorized
        '404':
          description: Workspace not found
      x-code-samples:
        - label: Node.js
          lang: typescript
          source: |-
            await orq.models.importLitellm([
              {
                model_name: "gpt-4o-proxy",
                litellm_params: {
                  use_in_pass_through: false,
                  use_litellm_proxy: true,
                  merge_reasoning_content_in_choices: false,
                  model: "openai/gpt-4o",
                },
                model_info: {
                  id: null, db_model: null, key: null, litellm_provider: "openai", mode: "chat",
                  input_cost_per_token: 0.0000025, output_cost_per_token: 0.00001,
                  supports_function_calling: true,
                  supported_openai_params: ["temperature", "max_tokens", "top_p"],
                },
              },
            ]);
components:
  schemas:
    LiteLLMModel:
      additionalProperties: false
      properties:
        litellm_params:
          $ref: '#/components/schemas/LiteLLMParams'
        model_info:
          $ref: '#/components/schemas/LiteLLMModelInfo'
        model_name:
          type: string
      required:
        - model_name
        - litellm_params
        - model_info
      type: object
    ModelDocument:
      additionalProperties: false
      properties:
        configuration:
          $ref: '#/components/schemas/ModelConfigurationResponse'
        created:
          type: string
        description:
          type:
            - string
            - 'null'
        display_name:
          type: string
        docs_url:
          type:
            - string
            - 'null'
        enabled:
          type: boolean
        enabled_for_endpoints:
          type: boolean
        enabled_for_playground:
          type: boolean
        has_cpu_pricing:
          type: boolean
        has_functions:
          type: boolean
        id:
          type: string
        input_cost:
          format: double
          type:
            - number
            - 'null'
        input_currency:
          type: string
        is_active:
          type: boolean
        legacy_uuid:
          type: string
        metadata:
          $ref: '#/components/schemas/ModelMetadata'
        model_developer:
          type: string
        model_family:
          type: string
        model_id:
          type: string
        model_type:
          type: string
        output_cost:
          format: double
          type:
            - number
            - 'null'
        output_currency:
          type: string
        owner:
          type: string
        parameters:
          items:
            $ref: '#/components/schemas/ModelParameterDocument'
          type:
            - array
            - 'null'
        pricing_url:
          type:
            - string
            - 'null'
        provider:
          type: string
        refId:
          type: string
        sharing:
          $ref: '#/components/schemas/ModelSharingConfig'
        updated:
          type: string
      required:
        - id
        - created
        - updated
        - display_name
        - model_id
        - is_active
        - provider
        - owner
        - input_cost
        - input_currency
        - output_cost
        - output_currency
        - description
        - pricing_url
        - docs_url
        - model_type
        - has_functions
        - has_cpu_pricing
        - enabled_for_playground
        - enabled_for_endpoints
        - configuration
        - metadata
        - parameters
        - enabled
        - refId
      type: object
    LiteLLMParams:
      additionalProperties: false
      properties:
        merge_reasoning_content_in_choices:
          type: boolean
        model:
          type: string
        use_in_pass_through:
          type: boolean
        use_litellm_proxy:
          type: boolean
      required:
        - use_in_pass_through
        - use_litellm_proxy
        - merge_reasoning_content_in_choices
        - model
      type: object
    LiteLLMModelInfo:
      additionalProperties: false
      properties:
        db_model:
          type:
            - boolean
            - 'null'
        id:
          type:
            - string
            - 'null'
        input_cost_per_token:
          type: number
          format: double
        key:
          type:
            - string
            - 'null'
        litellm_provider:
          type:
            - string
            - 'null'
        max_input_tokens:
          format: int64
          type: integer
        max_output_tokens:
          format: int64
          type: integer
        mode:
          type:
            - string
            - 'null'
        output_cost_per_token:
          type: number
          format: double
        supported_openai_params:
          items:
            type: string
          type:
            - array
            - 'null'
        supports_function_calling:
          type: boolean
        supports_native_streaming:
          type: boolean
        supports_reasoning:
          type: boolean
        supports_response_schema:
          type: boolean
        supports_system_messages:
          type: boolean
        supports_tool_choice:
          type: boolean
        supports_vision:
          type: boolean
      required:
        - id
        - db_model
        - key
        - litellm_provider
        - mode
      type: object
    ModelConfigurationResponse:
      additionalProperties: false
      properties:
        api_key_env:
          type: string
        api_version:
          type: string
        auth_mode:
          type: string
        auth_type:
          type: string
        base_url:
          type: string
        deployment_name:
          type: string
        endpoint:
          type: string
        inference_profile_arn:
          type: string
        integration_id:
          type: string
        is_openai_compatible:
          type: boolean
        is_tuned_model:
          type: boolean
        location:
          type: string
        project_id:
          type: string
        provider:
          type: string
        region:
          type: string
        should_use_beta_features:
          type: boolean
        subtype:
          type: string
        workspace_id:
          type: string
      required:
        - provider
      type: object
    ModelMetadata:
      additionalProperties: false
      properties:
        allowed_passthrough_parameters:
          items:
            type: string
          type:
            - array
            - 'null'
        autorouter:
          $ref: '#/components/schemas/AutoRouterConfig'
        batch_endpoints:
          items:
            type: string
          type:
            - array
            - 'null'
        cached_image_input_cost:
          type: number
          format: double
        cached_input_cost:
          type: number
          format: double
        chain_of_thought:
          type: boolean
        context_length:
          format: int64
          type: integer
        context_window:
          format: int64
          type: integer
        cost_efficiency_rating:
          format: int64
          type: integer
        cost_per_image:
          type: number
          format: double
        deprecation_date:
          type: string
        embedding_dimensions:
          format: int64
          type: integer
        extended_context_pricing_mode:
          type: string
        extended_context_threshold:
          format: int64
          type: integer
        function_tools_require_effort_none:
          type: boolean
        generate_audio:
          type: boolean
        image_input_cost:
          type: number
          format: double
        image_output_cost:
          type: number
          format: double
        image_token_cost:
          type: number
          format: double
        intelligence_rating:
          format: int64
          type: integer
        is_private:
          type: boolean
        is_realtime:
          type: boolean
        knowledge_cutoff:
          type: string
        max_images_per_request:
          format: int64
          type: integer
        max_input_tokens:
          format: int64
          type: integer
        max_output_tokens:
          format: int64
          type: integer
        max_temperature:
          type: number
          format: double
        million_searches_cost:
          type: number
          format: double
        million_tokens_above_128k_cache_read_cost:
          type: number
          format: double
        million_tokens_above_128k_cache_write_cost:
          type: number
          format: double
        million_tokens_above_128k_input_cost:
          type: number
          format: double
        million_tokens_above_128k_output_cost:
          type: number
          format: double
        million_tokens_above_200k_cache_read_cost:
          type: number
          format: double
        million_tokens_above_200k_cache_write_cost:
          type: number
          format: double
        million_tokens_above_200k_input_cost:
          type: number
          format: double
        million_tokens_above_200k_output_cost:
          type: number
          format: double
        million_tokens_audio_input_cost:
          type: number
          format: double
        million_tokens_audio_output_cost:
          type: number
          format: double
        million_tokens_batches_input_cost:
          type: number
          format: double
        million_tokens_batches_output_cost:
          type: number
          format: double
        million_tokens_cache_read_cost:
          type: number
          format: double
        million_tokens_cache_write_1h_cost:
          type: number
          format: double
        million_tokens_cache_write_5m_cost:
          type: number
          format: double
        million_tokens_cache_write_cost:
          type: number
          format: double
        million_tokens_input_cost:
          type: number
          format: double
        million_tokens_output_cost:
          type: number
          format: double
        million_tokens_reasoning_cost:
          type: number
          format: double
        multilingual:
          type: boolean
        offline:
          type: boolean
        per_video_second_cost:
          type: number
          format: double
        per_video_second_cost_1080p:
          type: number
          format: double
        pricing:
          $ref: '#/components/schemas/Pricing'
        reasoning_cost:
          type: number
          format: double
        reasoning_tokens:
          format: int64
          type: integer
        region:
          type: string
        speed_rating:
          format: int64
          type: integer
        supported_embedding_dimensions:
          $ref: '#/components/schemas/EmbeddingDimensionSupport'
        supported_video_aspect_ratios:
          items:
            type: string
          type:
            - array
            - 'null'
        supported_video_durations:
          items:
            format: int64
            type: integer
          type:
            - array
            - 'null'
        supported_video_frame_images:
          items:
            type: string
          type:
            - array
            - 'null'
        supported_video_resolutions:
          items:
            type: string
          type:
            - array
            - 'null'
        supported_video_sizes:
          items:
            type: string
          type:
            - array
            - 'null'
        supports_adaptive_reasoning:
          type: boolean
        supports_audio_input:
          type: boolean
        supports_audio_output:
          type: boolean
        supports_b64_json_response_format:
          type: boolean
        supports_batch_api:
          type: boolean
        supports_cache_control:
          type: boolean
        supports_citations:
          type: boolean
        supports_code_execution:
          type: boolean
        supports_commercial_use:
          type: boolean
        supports_computer_use:
          type: boolean
        supports_developer_message:
          type: boolean
        supports_direct_cost:
          type: boolean
        supports_distillation:
          type: boolean
        supports_extended_thinking:
          type: boolean
        supports_fine_tuning:
          type: boolean
        supports_google_realtime_api:
          type: boolean
        supports_image_edit:
          type: boolean
        supports_image_input:
          type: boolean
        supports_image_output:
          type: boolean
        supports_images:
          type: boolean
        supports_json_mode_response_format:
          type: boolean
        supports_json_schema_response_format:
          type: boolean
        supports_max_completion_tokens:
          type: boolean
        supports_openai_realtime_api:
          type: boolean
        supports_openai_sdk:
          type: boolean
        supports_parallel_tool_calls:
          type: boolean
        supports_pdf_input:
          type: boolean
        supports_prompt_caching:
          type: boolean
        supports_reasoning:
          type: boolean
        supports_reasoning_effort_default:
          type: boolean
        supports_reasoning_effort_high:
          type: boolean
        supports_reasoning_effort_low:
          type: boolean
        supports_reasoning_effort_max:
          type: boolean
        supports_reasoning_effort_medium:
          type: boolean
        supports_reasoning_effort_minimal:
          type: boolean
        supports_reasoning_effort_none:
          type: boolean
        supports_reasoning_effort_xhigh:
          type: boolean
        supports_responses_api:
          type: boolean
        supports_sampling_params:
          type: boolean
        supports_service_tier:
          type: boolean
        supports_streaming:
          type: boolean
        supports_strict_tool:
          type: boolean
        supports_structured_outputs:
          type: boolean
        supports_system_message:
          type: boolean
        supports_text:
          type: boolean
        supports_text_input:
          type: boolean
        supports_text_output:
          type: boolean
        supports_thinking_level:
          type: boolean
        supports_thinking_level_low:
          type: boolean
        supports_thinking_level_medium:
          type: boolean
        supports_thinking_level_minimal:
          type: boolean
        supports_tool_calling:
          type: boolean
        supports_tool_choice:
          type: boolean
        supports_url_context:
          type: boolean
        supports_url_response_format:
          type: boolean
        supports_video_input:
          type: boolean
        supports_video_output:
          type: boolean
        supports_video_seed:
          type: boolean
        supports_vision:
          type: boolean
        supports_web_search:
          type: boolean
        supports_zdr:
          type: boolean
        thinking_enforced:
          type: boolean
      required:
        - is_private
      type: object
    ModelParameterDocument:
      additionalProperties: false
      properties:
        config:
          type: object
          additionalProperties: {}
        description:
          type:
            - string
            - 'null'
        hints:
          type: string
        id:
          type: string
        is_active:
          type: boolean
        name:
          type: string
        parameter:
          type: string
        parameter_type:
          type: string
        position:
          format: int64
          type: integer
      required:
        - id
        - name
        - parameter
        - description
        - config
        - parameter_type
        - is_active
      type: object
    ModelSharingConfig:
      additionalProperties: false
      properties:
        allow_fork:
          type: boolean
        allow_version_pin:
          type: boolean
        auto_grant_new_projects:
          type: boolean
        mode:
          type: string
        project_ids:
          items:
            type: string
          type:
            - array
            - 'null'
      required:
        - mode
        - allow_version_pin
        - allow_fork
        - auto_grant_new_projects
      type: object
    AutoRouterConfig:
      additionalProperties: false
      properties:
        economical_model:
          type: string
        id:
          type: string
        models:
          items:
            type: string
          type:
            - array
            - 'null'
        profile:
          type: string
        strong_model:
          type: string
        v2:
          $ref: '#/components/schemas/AutoRouterV2Config'
        version:
          type: string
      type: object
    Pricing:
      additionalProperties: false
      properties:
        audio_input:
          $ref: '#/components/schemas/Price'
        audio_output:
          $ref: '#/components/schemas/Price'
        cache_read:
          $ref: '#/components/schemas/Price'
        cache_write_1h:
          $ref: '#/components/schemas/Price'
        cache_write_5m:
          $ref: '#/components/schemas/Price'
        input:
          $ref: '#/components/schemas/Price'
        output:
          $ref: '#/components/schemas/Price'
        reasoning:
          $ref: '#/components/schemas/Price'
        variants:
          items:
            $ref: '#/components/schemas/PricingVariant'
          type:
            - array
            - 'null'
      type: object
    EmbeddingDimensionSupport:
      additionalProperties: false
      properties:
        max:
          format: int64
          type: integer
        min:
          format: int64
          type: integer
        options:
          items:
            format: int64
            type: integer
          type:
            - array
            - 'null'
      type: object
    AutoRouterV2Config:
      additionalProperties: false
      properties:
        aa_creator:
          $ref: '#/components/schemas/AutoRouterV2CreatorConfig'
        aa_evaluations:
          additionalProperties:
            format: double
            type:
              - number
              - 'null'
          type: object
        aa_median_output_tokens_per_second:
          type: number
          format: double
        aa_median_time_to_first_answer_token:
          type: number
          format: double
        aa_median_time_to_first_token_seconds:
          type: number
          format: double
        aa_model_id:
          type: string
        aa_name:
          type: string
        aa_pricing:
          additionalProperties:
            format: double
            type:
              - number
              - 'null'
          type: object
        aa_release_date:
          type: string
        aa_slug:
          type: string
        default_effort:
          type: string
        intelligence_index:
          type: number
          format: double
        price:
          type: number
          format: double
        reasoning_efforts:
          additionalProperties:
            $ref: '#/components/schemas/AutoRouterV2EffortConfig'
          type: object
      required:
        - intelligence_index
        - price
      type: object
    Price:
      additionalProperties: false
      properties:
        cost:
          type: number
          format: double
        currency:
          type: string
        per:
          format: int64
          type: integer
        unit:
          type: string
      required:
        - cost
        - currency
        - unit
        - per
      type: object
    PricingVariant:
      additionalProperties: false
      properties:
        audio_input:
          $ref: '#/components/schemas/Price'
        audio_output:
          $ref: '#/components/schemas/Price'
        cache_read:
          $ref: '#/components/schemas/Price'
        cache_write_1h:
          $ref: '#/components/schemas/Price'
        cache_write_5m:
          $ref: '#/components/schemas/Price'
        input:
          $ref: '#/components/schemas/Price'
        output:
          $ref: '#/components/schemas/Price'
        reasoning:
          $ref: '#/components/schemas/Price'
        when:
          type: string
      required:
        - when
      type: object
    AutoRouterV2CreatorConfig:
      additionalProperties: false
      properties:
        id:
          type: string
        name:
          type: string
        slug:
          type: string
      required:
        - id
        - name
        - slug
      type: object
    AutoRouterV2EffortConfig:
      additionalProperties: false
      properties:
        aa_slug:
          type: string
        intelligence_index:
          type: number
          format: double
      required:
        - intelligence_index
      type: object
  securitySchemes:
    ApiKey:
      type: http
      scheme: bearer
      bearerFormat: JWT

````