client.generationModels.list()

import { createClient } from "@toloka-platform/sdk";

const client = createClient({
  baseUrl: "https://platform.toloka.ai",
  apiKey: process.env.TOLOKA_API_KEY!,
});

const catalog = await client.generationModels.list();
console.log(catalog);

{
  "defaultGenerationModelId": "gpt-5.4",
  "generationModels": [
    {
      "id": "gpt-5.4",
      "displayName": "<string>",
      "description": "<string>",
      "recommended": false,
      "budgets": [
        {
          "min": 0,
          "typical": 0,
          "maxEstimate": 0
        }
      ]
    }
  ]
}

import { createClient } from "@toloka-platform/sdk";

const client = createClient({
  baseUrl: "https://platform.toloka.ai",
  apiKey: process.env.TOLOKA_API_KEY!,
});

const catalog = await client.generationModels.list();
console.log(catalog);

{
  "defaultGenerationModelId": "gpt-5.4",
  "generationModels": [
    {
      "id": "gpt-5.4",
      "displayName": "<string>",
      "description": "<string>",
      "recommended": false,
      "budgets": [
        {
          "min": 0,
          "typical": 0,
          "maxEstimate": 0
        }
      ]
    }
  ]
}

Return the available models, supported reasoning efforts, and cost limits for synthetic generation. Use id as generationModelId. Set reasoningEffort only when defaultReasoningEffort is present. maxCostPerAttempt must be between min and maxEstimate; values below typical produce a warning.

Signature

Method signature on client.generationModels:

list(): Promise<{ defaultGenerationModelId: "gpt-5.6-terra" | "gpt-5.6-luna" | "gpt-5.4" | "gpt-5.4-mini" | "claude-sonnet-4-6" | "gemini-3.1-pro-preview" | "gemini-3.5-flash" | "gemini-3.7-flash" | "claude-sonnet-5" | "claude-opus-5" | "claude-fable-5" | "gpt-5.6-sol"; generationModels: GenerationModel[] }>;

Parameters

This method takes no arguments.

Returns

Promise<{ defaultGenerationModelId: "gpt-5.6-terra" | "gpt-5.6-luna" | "gpt-5.4" | "gpt-5.4-mini" | "claude-sonnet-4-6" | "gemini-3.1-pro-preview" | "gemini-3.5-flash" | "gemini-3.7-flash" | "claude-sonnet-5" | "claude-opus-5" | "claude-fable-5" | "gpt-5.6-sol"; generationModels: GenerationModel[] }>

required

The model a synthetic node uses when generationModelId is omitted.

GenerationModel[]

required

Models available for synthetic generation nodes.

Show Fields

required

The model id. Use it as generationModelId in a synthetic audienceAndPricing.

string

required

The model name the platform UI shows.

string

required

What the model is suited for.

boolean

required

Whether the platform recommends this model.

"low" | "medium" | "high"

The reasoning effort used when reasoningEffort is omitted. Absent when the model does not support reasoning effort; then setting reasoningEffort fails validation.

GenerationBudget[]

required

The maxCostPerAttempt bounds for each supported reasoning effort, or one entry without it.See the HTTP endpoint for the complete schema.

Errors

HTTP errors throw PotatoApiError. The endpoint documents these error responses:

Status	Description
429	Rate limit exceeded

HTTP endpoint: GET /generation-models.

import { createClient } from "@toloka-platform/sdk";

const client = createClient({
  baseUrl: "https://platform.toloka.ai",
  apiKey: process.env.TOLOKA_API_KEY!,
});

const catalog = await client.generationModels.list();
console.log(catalog);

{
  "defaultGenerationModelId": "gpt-5.4",
  "generationModels": [
    {
      "id": "gpt-5.4",
      "displayName": "<string>",
      "description": "<string>",
      "recommended": false,
      "budgets": [
        {
          "min": 0,
          "typical": 0,
          "maxEstimate": 0
        }
      ]
    }
  ]
}

Reference

TypeScript SDK

CLI

HTTP API

client.generationModels.list()

Signature

Parameters

Returns

Errors

​Signature

​Parameters

​Returns

​Errors

Signature

Parameters

Returns

Errors