API Reference

Copy Markdown

Open in Claude

Open in ChatGPT

Open in Cursor

---

Copy Markdown

View as Markdown

Techniques

Technique catalog endpoints.

Get a technique

client.techniques.retrieve(stringtechniqueID, RequestOptionsoptions?): TechniqueRetrieveResponse { inputs, name, outputs, 3 more }

GET/techniques/{techniqueId}

List techniques

client.techniques.list(TechniqueListParams { cursor, limit, query, workspace_id } query?, RequestOptionsoptions?): TechniquesCursorPage<TechniqueListResponse { inputs, name, outputs, 3 more } >

GET/techniques

ModelsExpand Collapse

TechniqueRetrieveResponse { inputs, name, outputs, 3 more }

inputs: Array<Input>

id: string

Technique input or output identifier

name: string

Technique input or output display name

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Technique input or output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

description?: string

Technique input or output description

specified_aspect_ratio?: string

Required aspect ratio

specified_duration?: number

Required duration in seconds

name: string

Technique name

outputs: Array<Output>

id: string

Technique input or output identifier

name: string

Technique input or output display name

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Technique input or output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

description?: string

Technique input or output description

specified_aspect_ratio?: string

Required aspect ratio

specified_duration?: number

Required duration in seconds

run_cost: number

technique_id: string

Technique identifier

description?: string

Technique description

TechniqueListResponse { inputs, name, outputs, 3 more }

inputs: Array<Input>

id: string

Technique input or output identifier

name: string

Technique input or output display name

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Technique input or output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

description?: string

Technique input or output description

specified_aspect_ratio?: string

Required aspect ratio

specified_duration?: number

Required duration in seconds

name: string

Technique name

outputs: Array<Output>

id: string

Technique input or output identifier

name: string

Technique input or output display name

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Technique input or output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

description?: string

Technique input or output description

specified_aspect_ratio?: string

Required aspect ratio

specified_duration?: number

Required duration in seconds

run_cost: number

technique_id: string

Technique identifier

description?: string

Technique description

TechniquesRuns

Nested technique run endpoints.

Start a technique run

client.techniques.runs.create(stringtechniqueID, RunCreateParams { inputs, mode, callback_url, idempotency_key } body, RequestOptionsoptions?): RunCreateResponse { created_at, progress, run_id, 8 more }

POST/techniques/{techniqueId}/runs

Get a technique run

client.techniques.runs.retrieve(stringrunID, RunRetrieveParams { techniqueId } params, RequestOptionsoptions?): RunRetrieveResponse { created_at, progress, run_id, 8 more }

GET/techniques/{techniqueId}/runs/{runId}

ModelsExpand Collapse

RunCreateResponse { created_at, progress, run_id, 8 more }

created_at: number

progress: number

run_id: string

Run identifier

status: "pending" | "running" | "completed" | "failed"

One of the following:

"pending"

"running"

"completed"

"failed"

charged_cost?: number

completed_at?: number

error_code?: string

Machine-readable run error code

error_message?: string

Human-readable run error message

outputs?: Array<Output>

output_id: string

Run output identifier

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Run output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

url: string

Run output URL

formaturi

poll_url?: string

formaturi

started_at?: number

RunRetrieveResponse { created_at, progress, run_id, 8 more }

created_at: number

progress: number

run_id: string

Run identifier

status: "pending" | "running" | "completed" | "failed"

One of the following:

"pending"

"running"

"completed"

"failed"

charged_cost?: number

completed_at?: number

error_code?: string

Machine-readable run error code

error_message?: string

Human-readable run error message

outputs?: Array<Output>

output_id: string

Run output identifier

type: "imageUrl" | "videoUrl" | "audioUrl" | 2 more

Run output media type

One of the following:

"imageUrl"

"videoUrl"

"audioUrl"

"text"

"documentUrl"

url: string

Run output URL

formaturi

poll_url?: string

formaturi

started_at?: number