Models

ModelService manages LLM models at the WORKSPACE level. Models represent available LLM providers and families (e.g., "anthropic/claude-sonnet-4.6"). Models are seeded into workspaces and can be enabled or disabled. All operations are implicitly scoped to the workspace determined by the JWT token.

Authentication: Bearer token (JWT) Scope: Workspace-level operations

List models

client.models.list(?, ?): CursorPagination<Model { metadata, spec } >

GET/v1/models

Get a model by ID

client.models.retrieve(, ?): Model { metadata, spec }

GET/v1/models/{id}

Set model status

client.models.setStatus(, , ?): Model { metadata, spec }

PUT/v1/models/{id}/status

ModelsExpand Collapse

Model { metadata, spec }

metadata: ResourceMetadata { id, accountId, createdAt, 5 more }

Standard metadata for persistent, named resources (e.g., agents, tools, prompts)

id: string

Unique identifier for the resource (prefixed ULID, e.g., "agent_01HXK...")

accountId: string

Account this resource belongs to for multi-tenant isolation (prefixed ULID)

createdAt: string

Timestamp when this resource was created

formatdate-time

name: string

Human-readable name for the resource (e.g., "Customer Support Agent", "Email Tool") Required for resources that users interact with directly

profileId: string

ID of the actor (user or service account) that created this resource

workspaceId: string

Workspace this resource belongs to for organizational grouping (prefixed ULID)

externalId?: string

External ID for the resource (e.g., a workflow ID from an external system)

labels?: Record<string, string>

Arbitrary key-value pairs for categorization and filtering Examples: {"environment": "production", "team": "platform", "version": "v2"}

spec: ModelSpec { family, inputPricePerMillionTokens, maxInputTokens, 4 more }

Model specification

family?: string

The model family (e.g., "claude-sonnet-4.6", "gpt-5.4", "gemini-2.5-flash")

inputPricePerMillionTokens?: string

Cost per million input tokens in cents (e.g., 300 = $3.00)

maxInputTokens?: number

Maximum number of input tokens the model supports

formatint32

maxOutputTokens?: number

Maximum number of output tokens the model can generate

formatint32

outputPricePerMillionTokens?: string

Cost per million output tokens in cents (e.g., 1500 = $15.00)

provider?: string

The model provider (e.g., "anthropic", "openai", "google")

status?: "MODEL_STATUS_UNSPECIFIED" | "MODEL_STATUS_ENABLED" | "MODEL_STATUS_DISABLED"

The status of the model in the workspace

formatenum

One of the following:

"MODEL_STATUS_UNSPECIFIED"

"MODEL_STATUS_ENABLED"

"MODEL_STATUS_DISABLED"

ModelSpec { family, inputPricePerMillionTokens, maxInputTokens, 4 more }

family?: string

The model family (e.g., "claude-sonnet-4.6", "gpt-5.4", "gemini-2.5-flash")

inputPricePerMillionTokens?: string

Cost per million input tokens in cents (e.g., 300 = $3.00)

maxInputTokens?: number

Maximum number of input tokens the model supports

formatint32

maxOutputTokens?: number

Maximum number of output tokens the model can generate

formatint32

outputPricePerMillionTokens?: string

Cost per million output tokens in cents (e.g., 1500 = $15.00)

provider?: string

The model provider (e.g., "anthropic", "openai", "google")

status?: "MODEL_STATUS_UNSPECIFIED" | "MODEL_STATUS_ENABLED" | "MODEL_STATUS_DISABLED"

The status of the model in the workspace

formatenum

One of the following:

"MODEL_STATUS_UNSPECIFIED"

"MODEL_STATUS_ENABLED"

"MODEL_STATUS_DISABLED"