> ## 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. # Retrieve a model catalog entry > Retrieves a single catalog entry by its id, `/` (for example `openai/gpt-4o`). Unlike the list endpoints this also resolves deprecated models; check `deprecated` and `deprecation` on the response. ## OpenAPI ````yaml get /v2/model-catalog/{id} openapi: 3.1.0 info: title: orq.ai API version: '2.0' description: orq.ai API documentation servers: - url: https://api.orq.ai security: - ApiKey: [] tags: - name: Chunking description: Split text into smaller chunks for retrieval and generation workflows. - 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. - 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: API keys description: >- API keys authenticate programmatic access to the workspace. The unified key model exposes opaque tokens, per-domain access grants, and budget / rate-limit constraints (see ADR 0001 and ADR 0002). - name: Budgets description: >- Budgets govern spend, token usage, and request rate across six scopes: workspace, project, identity, api-key, provider, and model. A budget is hierarchical and defense-in-depth — every applicable budget is a hard gate, and the most restrictive one wins per dimension (see ADR 0007). - name: Documentation description: >- Search the orq.ai documentation. Proxies the workspace's query to the hosted docs search index. - name: Files description: File upload and retrieval operations. - name: Finder description: >- Finder entities back the studio navigation tree, project switcher, and cross-project resource references. - 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: 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: >- Manage upstream MCP servers and client-facing MCP gateways. Create server connections, discover tools, assemble gateways, and review call logs. - name: Model Catalog description: >- Browse the orq.ai model catalog: every model orq offers, across every provider, with pricing, capabilities and benchmark data. 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: Model Sharing description: >- Model sharing controls which projects a workspace model is available to. Workspace admins configure a model's Sharing (all projects / selected projects); the config ships inline on the models list response, so there is no separate read endpoint. - 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: 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: 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: 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. externalDocs: url: https://docs.orq.ai description: orq.ai Documentation paths: /v2/model-catalog/{id}: get: tags: - Model Catalog summary: Retrieve a model catalog entry description: >- Retrieves a single catalog entry by its id, `/` (for example `openai/gpt-4o`). Unlike the list endpoints this also resolves deprecated models; check `deprecated` and `deprecation` on the response. operationId: ModelCatalogGet parameters: - schema: type: string description: >- Catalog identifier, `/` (for example `openai/gpt-4o`). required: true description: >- Catalog identifier, `/` (for example `openai/gpt-4o`). name: id in: path responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/GetModelCatalogModelResponse' security: [] x-code-samples: - lang: curl label: Core - Retrieve a model catalog entry source: | curl --get 'https://api.orq.ai/v2/model-catalog/openai/gpt-4o' - lang: python label: Python - Retrieve a model catalog entry source: | import os from orq_ai_sdk import Orq client = Orq(api_key=os.environ["ORQ_API_KEY"]) result = client.model_catalog.get( id="openai/gpt-4o", ) print(result.model.name, result.model.pricing) - lang: typescript label: Node.js - Retrieve a model catalog entry source: | import { Orq } from '@orq-ai/node'; const client = new Orq({ apiKey: process.env.ORQ_API_KEY, }); const result = await client.modelCatalog.get({ id: 'openai/gpt-4o', }); console.log(result.model.name, result.model.pricing); components: schemas: GetModelCatalogModelResponse: required: - model type: object properties: model: allOf: - $ref: '#/components/schemas/Model' description: Requested catalog entry. Model: required: - id - created - name - description - provider - endpoints - modalities - offering_of - supported_parameters - supported_tiers - location - features - deprecated type: object properties: id: type: string description: >- Catalog identifier, `/` (for example `openai/gpt-4o`). created: type: string description: |- When orq listed this offering, Unix seconds (string-encoded int64 in JSON). deprecation: type: string description: |- When this offering stops being served, Unix seconds (string-encoded int64 in JSON): orq's own sunset date if one is set, otherwise the developer's announced deprecation date. Absent when neither is set. name: type: string description: Display name shown in the orq model garden. description: type: string description: Short model description. provider: allOf: - $ref: '#/components/schemas/ModelProvider' description: Provider that serves this offering. endpoints: type: array items: type: string description: API endpoints this offering exposes (chat, batch, ...). modalities: allOf: - $ref: '#/components/schemas/ModelModalities' description: Content modalities this offering consumes and produces. offering_of: type: string description: >- Provider-independent model reference this offering serves, `/`. pricing: type: object description: |- Resolved commercial pricing, including service-tier variants. Each variant carries a `when` CEL condition string evaluated against `input_tokens`, `output_tokens`, `total_tokens` and `tier`; all variants whose condition is true are merged onto the base pricing in order, later variants winning per field. Absent when this offering has no representable token-based pricing. supported_parameters: type: array items: type: string description: >- API parameter keys this offering accepts, snake_case (e.g. `temperature`, `max_tokens`). supported_tiers: type: array items: type: string description: Paid service tier names available to this offering. context_window: type: string description: |- Maximum input context size in tokens (string-encoded int64 in JSON). Absent when not applicable. location: type: array items: type: string description: Regions this offering routes to, lowercased. artificial_intelligence: type: object description: >- Artificial Analysis benchmark scores keyed by evaluation name. Absent when unavailable for this offering. features: type: array items: type: string description: |- Normalized capability names this offering supports, snake_case and alphabetical (e.g. `json_mode`, `tool_calling`, `vision`, `web_search`). deprecated: type: boolean description: |- True when this offering is deprecated, whether or not a deprecation date is known. `deprecation` carries the date when one is announced. ModelProvider: required: - id - logo type: object properties: id: type: string description: Catalog provider key (openai, anthropic, aws, ...). logo: type: string description: Absolute URL of the provider logo. Empty when no logo is known. ModelModalities: required: - input - output type: object properties: input: type: array items: type: string description: Modalities this offering accepts as input. output: type: array items: type: string description: Modalities this offering produces as output. securitySchemes: ApiKey: type: http scheme: bearer bearerFormat: JWT ````