> ## Documentation Index > Fetch the complete documentation index at: https://doc.featherhq.com/llms.txt > Use this file to discover all available pages before exploring further. # List models, per-role runtime defaults, and the system default fallback chain > Selectable models + the code-default model each runtime role falls back to. The role defaults mirror the runtime constants (single-sourced via ``src.runtime.model_defaults.ROLE_DEFAULTS``, which imports the SAME constants the runtime applies) so the UI can show what's actually used — model + effort + max_tokens + temperature + thinking budget — when an entity leaves a setting unset. Imported lazily inside the handler: ``model_router`` deliberately never imports ``src.runtime`` at module scope (the runtime imports ``model_router.service`` — a top-level import here risks a cycle). ## OpenAPI ````yaml /api-reference/openapi.json get /v1/model-router/catalog openapi: 3.1.0 info: title: Feather API description: >- Unified customer experience platform API. Manages identity, conversations, memory, agents, procedures, policies, model routing, knowledge bases, integrations, and runtime execution. version: 1.87.0 servers: - url: https://api-sandbox.featherhq.com description: Sandbox - url: http://localhost:8000 description: Local dev security: [] paths: /v1/model-router/catalog: get: tags: - model-router summary: >- List models, per-role runtime defaults, and the system default fallback chain description: >- Selectable models + the code-default model each runtime role falls back to. The role defaults mirror the runtime constants (single-sourced via ``src.runtime.model_defaults.ROLE_DEFAULTS``, which imports the SAME constants the runtime applies) so the UI can show what's actually used — model + effort + max_tokens + temperature + thinking budget — when an entity leaves a setting unset. Imported lazily inside the handler: ``model_router`` deliberately never imports ``src.runtime`` at module scope (the runtime imports ``model_router.service`` — a top-level import here risks a cycle). operationId: getModelCatalog responses: '200': description: Successful Response content: application/json: schema: $ref: '#/components/schemas/ModelCatalogResponse' '400': description: Bad request content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' '401': description: Authentication required content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' security: - APIKeyHeader: [] components: schemas: ModelCatalogResponse: properties: models: items: $ref: '#/components/schemas/AvailableModel' type: array title: Models role_defaults: items: $ref: '#/components/schemas/RoleModelDefault' type: array title: Role Defaults default_chain: items: $ref: '#/components/schemas/ModelChainEntry' type: array title: Default Chain type: object required: - models - role_defaults - default_chain title: ModelCatalogResponse description: >- Selectable models, per-role code defaults, and the system default fallback chain. ``default_chain`` is the platform-level fallback chain (a hardcoded constant from ``src.model_router.defaults``) used when no org-level default router config exists. It is read-only — there is no API to mutate it. ErrorResponse: properties: error: type: string title: Error message: type: string title: Message retryable: anyOf: - type: boolean - type: 'null' title: Retryable retry_after: anyOf: - type: integer - type: 'null' title: Retry After type: object required: - error - message title: ErrorResponse description: Standard error response returned by all API error handlers. AvailableModel: properties: model_identifier: type: string title: Model Identifier provider: type: string title: Provider supports_streaming: type: boolean title: Supports Streaming supports_tools: type: boolean title: Supports Tools default: true supports_vision: type: boolean title: Supports Vision default: false max_context_window: type: integer title: Max Context Window regions: items: type: string type: array title: Regions family: type: string title: Family default: default supports_json_schema: type: boolean title: Supports Json Schema default: true supports_reasoning_effort: type: boolean title: Supports Reasoning Effort default: false allowed_efforts: items: type: string type: array title: Allowed Efforts fastest_effort: anyOf: - type: string - type: 'null' title: Fastest Effort supports_temperature: type: boolean title: Supports Temperature default: true supports_thinking: type: boolean title: Supports Thinking default: false supports_thinking_budget: type: boolean title: Supports Thinking Budget default: false supports_audio: type: boolean title: Supports Audio default: false compliance_tags: items: type: string type: array title: Compliance Tags input_price_per_1m: type: number title: Input Price Per 1M output_price_per_1m: type: number title: Output Price Per 1M type: object required: - model_identifier - provider - supports_streaming - max_context_window - input_price_per_1m - output_price_per_1m title: AvailableModel RoleModelDefault: properties: role: type: string title: Role model: type: string title: Model reasoning_effort: anyOf: - type: string - type: 'null' title: Reasoning Effort max_tokens: anyOf: - type: integer - type: 'null' title: Max Tokens temperature: anyOf: - type: number - type: 'null' title: Temperature thinking_budget: anyOf: - type: integer - type: 'null' title: Thinking Budget type: object required: - role - model title: RoleModelDefault description: >- A runtime role and its code-default model + generation settings. Surfaces the constants the runtime uses when an entity (agent/team/workflow) has not configured a model, so the UI can show "uses default: ". ModelChainEntry: properties: model: type: string title: Model config: $ref: '#/components/schemas/ModelConfig' type: object required: - model title: ModelChainEntry ModelConfig: properties: temperature: anyOf: - type: number maximum: 2 minimum: 0 - type: 'null' title: Temperature max_tokens: anyOf: - type: integer minimum: 1 - type: 'null' title: Max Tokens top_p: anyOf: - type: number maximum: 1 minimum: 0 - type: 'null' title: Top P stop_sequences: anyOf: - items: type: string type: array maxItems: 8 - type: 'null' title: Stop Sequences reasoning_effort: anyOf: - type: string enum: - none - minimal - low - medium - high - xhigh - max - type: 'null' title: Reasoning Effort request_timeout_ms: anyOf: - type: integer maximum: 20000 minimum: 1000 - type: 'null' title: Request Timeout Ms thinking_budget: anyOf: - type: integer minimum: 1 - type: 'null' title: Thinking Budget type: object title: ModelConfig securitySchemes: APIKeyHeader: type: apiKey in: header name: x-api-key ````