ThankYou TypeScript SDK

Official TypeScript SDK for the ThankYou unified creative generation API.

npm install @thankyouai/sdk

The package supports both ESM and CommonJS on Node.js 18 and newer.

Create a Client

ESM:

import { ThankYou } from "@thankyouai/sdk";

const thankyou = new ThankYou({
  apiKey: process.env.THANKYOU_API_KEY!,
});

CommonJS:

const { ThankYou } = require("@thankyouai/sdk");

const thankyou = new ThankYou({
  apiKey: process.env.THANKYOU_API_KEY,
});

The default base URL is https://api.thankyouai.com/open/v1.

Text to Image

const result = await thankyou.run({
  model: "flux/v2/pro/text-to-image",
  input: {
    prompt: "A mountain landscape at golden hour",
    aspect_ratio: "16:9",
  },
});

console.log(result.output[0]?.url);

Image to Video with an Uploaded File

const file = await thankyou.files.upload({
  file: "./photo.jpg",
});

const generation = await thankyou.generations.create({
  model: "wan/v2.6",
  input: {
    prompt: "Gentle camera movement with soft evening light",
    reference_assets: [{ role: "primary", url: file.url }],
  },
});

const result = await thankyou.generations.wait(generation.id, {
  interval: 3000,
  timeout: 10 * 60 * 1000,
});

Quote Before Execute

Use a quote when you want to estimate the cost and check whether a request can run before starting the generation. A quote returns the resolved input, estimated cost, blocking reasons, and an expiration time.

const quote = await thankyou.generations.quote({
  model: "wan/v2.6",
  input: { prompt: "A koi fish swimming", duration: 5 },
});

if (quote.blocking_reasons.length > 0) {
  throw new Error(quote.blocking_reasons.join(", "));
}

console.log(quote.estimated_cost, quote.currency, quote.expires_at);

const generation = await thankyou.generations.create({
  quoteId: quote.quote_id,
});

Models

const models = await thankyou.models.list();
const detail = await thankyou.models.detail("wan/v2.6");

console.log(models.models.length);
console.log(detail.input_schema);

Model IDs can contain /, so models.detail() calls GET /models/detail?model_id=....

Usage

const usage = await thankyou.usage.get({ days: 30 });

console.log(usage.media.total_tasks);
console.log(usage.llm.total_tokens);

LLM Requests

const requests = await thankyou.llmRequests.list({
  page: 1,
  pageSize: 20,
  status: "succeeded",
  modelPrefix: "gpt-",
});

console.log(requests.requests[0]?.request_id);

Webhook Verification

const event = thankyou.webhooks.verify({
  rawBody,
  signature: request.headers["x-thankyou-signature"],
  timestamp: request.headers["x-thankyou-timestamp"],
  secret: process.env.THANKYOU_WEBHOOK_SECRET!,
});

if (event.event === "generation.completed") {
  console.log(event.generation?.output[0]?.url);
}

The signature is HMAC-SHA256 over ${timestamp}.${rawBody} and is formatted as sha256=<hex>.

Error Handling

import {
  ThankYouAPIError,
  ThankYouAuthenticationError,
  ThankYouRateLimitError,
  ThankYouValidationError,
} from "@thankyouai/sdk";

try {
  await thankyou.generations.create({
    model: "wan/v2.6",
    input: { prompt: "test" },
  });
} catch (error) {
  if (error instanceof ThankYouRateLimitError) {
    console.error("Rate limited", error.code, error.details);
  } else if (error instanceof ThankYouValidationError) {
    console.error("Invalid request", error.details);
  } else if (error instanceof ThankYouAuthenticationError) {
    console.error("Check your API key");
  } else if (error instanceof ThankYouAPIError) {
    console.error(error.status, error.code, error.retryable, error.details);
  } else {
    throw error;
  }
}

Type Strategy

The SDK generates built-in model input types from the live developer API model list and each model's models.detail().input_schema. Dynamic or custom model IDs still fall back to generic JSON input.