Models

TypeScript

API reference for enhanced model methods.

The models resource is enhanced so that retrieve() returns a response where response.model has a .run() method. All other original methods (create, update, list, delete, copy, deleteImages, download, getBulk, transfer, updateTags, and the description, examples, presets, promptGuide, scores and trainingImages sub-resources) are inherited unchanged. train is enhanced: see Training.

`client.models.retrieve(modelID)`

Get a model by ID. Returns an enhanced response where response.model has .run().

Signature

client.models.retrieve(
  modelID: string,
  query?: ModelRetrieveParams | null,
  options?: RequestOptions,
): APIPromise<EnhancedModelRetrieveResponse>

Parameters

Name	Type	Description
`modelID`	`string`	The model ID to retrieve.
`query?`	`ModelRetrieveParams \| null`	Optional query parameters.

Returns

APIPromise<EnhancedModelRetrieveResponse> — the standard retrieve response with model enhanced:

Property	Type	Description
`model`	`ModelRetrieveResponse.Model & ModelEntity`	All original model fields plus `.run()`.

EnhancedModelRetrieveResponse and ModelEntity are not exported from the package root. Import them from @scenario-labs/sdk/lib/models if you need to name them.

Example

import Scenario from '@scenario-labs/sdk';

const client = new Scenario({ apiKey: '...', apiSecret: '...' });

const { model } = await client.models.retrieve('model_...');
console.log(model.id);   // original field
console.log(model.name); // original field

`model.run(params)`

Available on response.model after calling client.models.retrieve(). Generates with this model. Shortcut for client.generate.runModel(model.id, params) — no need to repeat the model ID. Returns an enhanced response where response.job has .wait(). See Jobs for the full .wait() reference.

Signature

response.model.run(
  params: GenerateRunModelParams,
  options?: RequestOptions,
): APIPromise<WithJob<GenerateRunModelResponse>>

Parameters

Name	Type	Description
`params.body`	`unknown`	Model-specific inputs (prompt, images, etc.). The accepted inputs come from `GET /models/{modelId}`.
`params.dryRun?`	`'true' \| 'api'`	Estimates the creative units cost (269 response) instead of running. `'api'` estimates at the API tier. The response then carries only the cost estimate (`creativeUnitsCost`) and no job, so don’t call `.wait()` on it.
`params.ipDetection?`	`boolean`	Runs an IP-detection preflight (Enterprise plan only). The detection fee is charged even with `dryRun`.
`params.projectId?`	`string`	Project that owns the resource.

If the model was retrieved with a projectId (the typed projectId param or options.query.projectId on retrieve(), or the client’s projectId), .run() reuses that project, and response.job.wait() polls in it too. An explicit non-empty projectId on this call, in params or options.query, wins over the captured project. An empty or unset one does not.

Returns

APIPromise<WithJob<GenerateRunModelResponse>> — a generate response where response.job has .wait().

Example

import Scenario from '@scenario-labs/sdk';

const client = new Scenario({ apiKey: '...', apiSecret: '...' });

const { model } = await client.models.retrieve('model_...');

const response = await model.run({
  body: { prompt: 'a medieval shield with dragon emblem' },
});

const completed = await response.job.wait();
console.log(completed.status);           // 'success'
console.log(completed.metadata?.assetIds);