> ## Documentation Index > Fetch the complete documentation index at: https://docs.kubiya.ai/llms.txt > Use this file to discover all available pages before exploring further. # List Models > List all LLM models from LiteLLM server with database fallback. Models are fetched dynamically from the configured LiteLLM server with caching for performance. Falls back to database models if LiteLLM is unavailable. Query Parameters: - provider: Filter by provider name (e.g., 'xai', 'anthropic', 'openai') - runtime: Filter by compatible runtime (e.g., 'claude_code', 'default') - type: Filter by model type (e.g., 'embedding', 'text-generation', 'multimodal') - skip/limit: Pagination **Example:** ``` GET /api/v1/models GET /api/v1/models?provider=xai GET /api/v1/models?runtime=claude_code GET /api/v1/models?type=embedding GET /api/v1/models?type=text-generation&provider=anthropic ``` ## OpenAPI ````yaml https://control-plane.kubiya.ai/api/openapi.json get /api/v1/models openapi: 3.1.0 info: title: Agent Control Plane API description: Multi-tenant agent orchestration with Temporal workflows version: 1.0.0 servers: [] security: - BearerAuth: [] tags: - name: health description: πŸ₯ **Health & Status** - Check API health and availability - name: authentication description: πŸ” **Authentication** - Token validation and auth management - name: agents description: πŸ€– **Agents** - Create and manage AI agents with custom capabilities - name: skills description: πŸ› οΈ **Tool Sets** - Manage agent skills and tool configurations - name: integrations description: πŸ”Œ **Integrations** - Connect to external services (Kubiya managed) - name: custom-integrations description: >- βš™οΈ **Custom Integrations** - User-defined integration instances with env vars, secrets, and files - name: integration-templates description: >- πŸ“¦ **Integration Templates** - Pre-configured templates for common services (PostgreSQL, Redis, MongoDB, etc.) - name: secrets description: πŸ”‘ **Secrets** - Secure credential storage and retrieval - name: teams description: πŸ‘₯ **Teams** - Team management and collaboration - name: workflows description: πŸ“Š **Workflows** - Multi-step automation and orchestration - name: executions description: ▢️ **Executions** - Track and monitor workflow runs - name: jobs description: ⏰ **Jobs** - Scheduled and webhook-triggered tasks - name: policies description: πŸ›‘οΈ **Policies** - Access control and security policies - name: analytics description: πŸ“ˆ **Analytics** - Usage metrics and performance monitoring - name: projects description: πŸ“ **Projects** - Project organization and management - name: environments description: 🌍 **Environments** - Environment configuration (dev, staging, prod) - name: models description: 🧠 **Models** - LLM model configuration and management - name: runtimes description: ⚑ **Runtimes** - Agent execution runtime environments - name: workers description: πŸ‘· **Workers** - Worker registration and heartbeat monitoring - name: storage description: πŸ’Ύ **Storage** - File storage and cloud integration - name: context-graph description: πŸ•ΈοΈ **Context Graph** - Knowledge graph and context management - name: temporal-workflows description: >- βš™οΈ **Temporal Workflows** - Background workflows for context graph ingestion, connector operations, and scheduled jobs - name: templates description: πŸ“ **Templates** - Reusable configuration templates paths: /api/v1/models: get: summary: List Models description: >- List all LLM models from LiteLLM server with database fallback. Models are fetched dynamically from the configured LiteLLM server with caching for performance. Falls back to database models if LiteLLM is unavailable. Query Parameters: - provider: Filter by provider name (e.g., 'xai', 'anthropic', 'openai') - runtime: Filter by compatible runtime (e.g., 'claude_code', 'default') - type: Filter by model type (e.g., 'embedding', 'text-generation', 'multimodal') - skip/limit: Pagination **Example:** ``` GET /api/v1/models GET /api/v1/models?provider=xai GET /api/v1/models?runtime=claude_code GET /api/v1/models?type=embedding GET /api/v1/models?type=text-generation&provider=anthropic ``` operationId: list_models_api_v1_models_get parameters: - name: provider in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by provider (e.g., 'xai', 'anthropic') title: Provider description: Filter by provider (e.g., 'xai', 'anthropic') - name: runtime in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by compatible runtime (e.g., 'claude_code') title: Runtime description: Filter by compatible runtime (e.g., 'claude_code') - name: type in: query required: false schema: anyOf: - type: string - type: 'null' description: Filter by model type (e.g., 'embedding', 'text-generation') title: Type description: Filter by model type (e.g., 'embedding', 'text-generation') - name: skip in: query required: false schema: type: integer minimum: 0 default: 0 title: Skip - name: limit in: query required: false schema: type: integer maximum: 1000 minimum: 1 default: 100 title: Limit responses: '200': description: Successful Response content: application/json: schema: type: array items: $ref: '#/components/schemas/LLMModelResponse' title: Response List Models Api V1 Models Get '422': description: Validation Error content: application/json: schema: $ref: '#/components/schemas/HTTPValidationError' components: schemas: LLMModelResponse: properties: id: type: string title: Id value: type: string title: Value label: type: string title: Label provider: type: string title: Provider model_type: type: string title: Model Type logo: anyOf: - type: string - type: 'null' title: Logo description: anyOf: - type: string - type: 'null' title: Description enabled: type: boolean title: Enabled recommended: type: boolean title: Recommended compatible_runtimes: items: type: string type: array title: Compatible Runtimes capabilities: additionalProperties: true type: object title: Capabilities pricing: anyOf: - additionalProperties: true type: object - type: 'null' title: Pricing display_order: type: integer title: Display Order created_at: type: string title: Created At updated_at: type: string title: Updated At type: object required: - id - value - label - provider - model_type - logo - description - enabled - recommended - compatible_runtimes - capabilities - pricing - display_order - created_at - updated_at title: LLMModelResponse description: Schema for LLM model responses HTTPValidationError: properties: detail: items: $ref: '#/components/schemas/ValidationError' type: array title: Detail type: object title: HTTPValidationError ValidationError: properties: loc: items: anyOf: - type: string - type: integer type: array title: Location msg: type: string title: Message type: type: string title: Error Type type: object required: - loc - msg - type title: ValidationError securitySchemes: BearerAuth: type: http scheme: bearer bearerFormat: JWT description: 'Enter your Kubiya API token (format: Bearer )' ````