---
title: "Get a model by ID"
method: GET
path: "/v1/workspaces/{workspaceId}/models/{id}"
tags: ["ModelService", "Models"]
---

# Get a model by ID

`GET /v1/workspaces/{workspaceId}/models/{id}`

Retrieves a model by ID from the workspace

## Path parameters

- `workspaceId` string, required
- `id` string, required

## Response `200`

OK

- Model
  - `metadata` ResourceMetadata, required — Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
    - `id` string, required — Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")
    - `accountId` string, required — Account this resource belongs to for multi-tenant isolation (prefixed ULID)
    - `workspaceId` string, required — Workspace this resource belongs to for organizational grouping (prefixed ULID)
    - `name` string, required — Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly
    - `externalId` string — External ID for the resource (e.g., a workflow ID from an external system)
    - `labels` object — Key-value pairs for categorization and filtering. Values are 0-63 alphanumeric characters with "-", "_", or "." allowed between; keys follow the same shape and additionally accept an optional DNS-subdomain prefix (e.g. "cadenya.com/") of at most 253 characters. Examples: {"environment": "production", "team": "platform", "version": "v2"}
    - `profileId` string, required — ID of the actor (user or service account) that created this resource
    - `createdAt` string, date-time, required — Timestamp when this resource was created
    - `updatedAt` string, date-time — Timestamp when this resource was last updated
  - `spec` ModelSpec, required
    - `provider` string, required — The model provider (e.g., "anthropic", "openai", "google")
    - `family` string, required — The model family (e.g., "claude-sonnet-4.6", "gpt-5.4", "gemini-2.5-flash")
    - `maxInputTokens` integer — Maximum number of input tokens the model supports
    - `maxOutputTokens` integer — Maximum number of output tokens the model can generate
    - `inputPricePerMillionTokens` string — Cost per million input tokens in cents (e.g., 300 = $3.00)
    - `outputPricePerMillionTokens` string — Cost per million output tokens in cents (e.g., 1500 = $15.00)
    - `reasoning` 'REASONING_UNSPECIFIED' | 'REASONING_NONE' | 'REASONING_ADAPTIVE' | 'REASONING_BUDGET' | 'REASONING_NONE' | 'REASONING_ADAPTIVE' | 'REASONING_BUDGET', enum — The model's reasoning capability. Catalog data used to decide whether thinking is requested for objective iterations on this model.
  - `info` ModelInfo — ModelInfo carries server-derived, read-only details about a model.
    - `aiProviderKey` AIProviderKey — AIProviderKey is a credential for an AI provider, scoped to a workspace. Most keys are customer-provided (BYOK); Cadenya also provisions promotional keys (see AIProviderKeyInfo.is_promotional), which cannot be modified or deleted by account administrators. The secret value is never returned in responses.
      - `metadata` ResourceMetadata, required — Standard metadata for persistent, named resources (e.g., agents, tools, prompts)
        - `id` string, required — Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")
        - `accountId` string, required — Account this resource belongs to for multi-tenant isolation (prefixed ULID)
        - `workspaceId` string, required — Workspace this resource belongs to for organizational grouping (prefixed ULID)
        - `name` string, required — Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly
        - `externalId` string — External ID for the resource (e.g., a workflow ID from an external system)
        - `labels` object — Key-value pairs for categorization and filtering. Values are 0-63 alphanumeric characters with "-", "_", or "." allowed between; keys follow the same shape and additionally accept an optional DNS-subdomain prefix (e.g. "cadenya.com/") of at most 253 characters. Examples: {"environment": "production", "team": "platform", "version": "v2"}
        - `profileId` string, required — ID of the actor (user or service account) that created this resource
        - `createdAt` string, date-time, required — Timestamp when this resource was created
        - `updatedAt` string, date-time — Timestamp when this resource was last updated
      - `spec` AIProviderKeySpec, required
        - `provider` 'AI_PROVIDER_UNSPECIFIED' | 'AI_PROVIDER_OPENROUTER' | 'AI_PROVIDER_OPENAI' | 'AI_PROVIDER_ANTHROPIC' | 'AI_PROVIDER_GEMINI' | 'AI_PROVIDER_OPENAI_COMPATIBLE', enum — The AI provider this key authenticates against.
        - `credentials` union — AIProviderCredential is the secret material used to authenticate with a provider. The set case must correspond to AIProviderKeySpec.provider. The server encrypts the serialized message at rest and never returns it on reads.
          - AIProviderCredentialApiKey
            - `type` 'apiKey', required
            - `apiKey` CredentialAPIKey, required — CredentialAPIKey carries a single bearer/header API key.
              - …
          - AIProviderCredentialHeaders
            - `type` 'headers', required
            - `headers` CredentialHeaders, required — CredentialHeaders carries arbitrary HTTP headers sent with every request to the provider (e.g. {"Authorization": "Bearer ...", "X-Api-Key": "..."}).
              - …
        - `config` union — AIProviderConfig holds non-secret, provider-specific settings. The set case must correspond to AIProviderKeySpec.provider. Providers with no settings (Anthropic, Gemini) simply leave this unset. The endpoint of a named provider is fixed and intentionally not overridable here; use the OpenAI-compatible provider to target a custom endpoint.
          - AIProviderConfigOpenrouter
            - `type` 'openrouter', required
            - `openrouter` OpenRouterConfig, required — OpenRouterConfig holds OpenRouter-specific settings.
              - …
          - AIProviderConfigOpenai
            - `type` 'openai', required
            - `openai` OpenAIConfig, required — OpenAIConfig holds OpenAI-specific settings.
              - …
          - AIProviderConfigOpenaiCompatible
            - `type` 'openaiCompatible', required
            - `openaiCompatible` OpenAICompatibleConfig, required — OpenAICompatibleConfig configures a generic endpoint that speaks the OpenAI Chat Completions API. The base URL is required and its model catalog is discovered live via GET {base_url}/models.
              - …
      - `info` AIProviderKeyInfo — AIProviderKeyInfo carries server-derived, read-only details about a key, for AI provider management UIs.
        - `enabledModelCount` integer — Number of enabled models provisioned on this key.
        - `disabledModelCount` integer — Number of disabled models provisioned on this key.
        - `isPromotional` boolean — Cadenya includes promotional keys (one for onboarding, and potentially more in the future). These are not added or maintained by account administrators.
    - `agentVariationCount` integer — Number of agent variations currently provisioned on this model. Useful for previewing how many variations a swap would affect.
    - `lastUsedAt` string, date-time — Represents the last time this model was used in an agent objective
  - `state` 'STATE_UNSPECIFIED' | 'STATE_ENABLED' | 'STATE_DISABLED', enum, required — Whether the model is usable in this workspace. Output only. Use the :enable and :disable actions to transition.

## Other responses

- `default` — Default error response

---

[API](https://skmtc.net/cadenya/apis/cadenya-api.md) · [All operations](https://skmtc.net/cadenya/apis/cadenya-api/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/cadenya/cadenya-api/versions/ac1a7f084068/schema)