Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.platform.decart.ai/llms.txt

Use this file to discover all available pages before exploring further.

We’ve updated video generation to use an asynchronous job-based Queue API. This change improves reliability, allows for better timeout handling, and provides visibility into job progress. The synchronous /v1/generate/ endpoints for video are now deprecated in favor of the new /v1/jobs/ endpoints.

​
What Changed

AspectBefore (Generate API)After (Queue API)
Endpoint/v1/generate/lucy-pro-t2v/v1/jobs/lucy-pro-t2v
Request typeSynchronous (blocking)Asynchronous (non-blocking)
ResponseDirect video binaryJob ID for polling
Timeout handlingHTTP timeout on long requestsPoll until completion (10 min max)
Progress visibilityNoneStatus updates (pending, processing, completed, failed)

​
JavaScript SDK

The JavaScript SDK now uses client.queue instead of client.generate for video generation.

​
Before

import { createDecartClient, models } from "@decartai/sdk";
import { writeFileSync } from "fs";

const client = createDecartClient({ apiKey: "your-api-key" });

// Synchronous - blocks until video is ready
const video = await client.generate({
  model: models.video("lucy-pro-t2v"),
  prompt: "A serene lake at sunset",
});

writeFileSync("output.mp4", Buffer.from(await video.arrayBuffer()));

​
After

import { createDecartClient, models } from "@decartai/sdk";
import { writeFileSync } from "fs";

const client = createDecartClient({ apiKey: "your-api-key" });

// Asynchronous - submit and poll for completion
const result = await client.queue.submitAndPoll({
  model: models.video("lucy-pro-t2v"),
  prompt: "A serene lake at sunset",
  onStatusChange: (job) => console.log(`Status: ${job.status}`),
});

if (result.status === "completed") {
  writeFileSync("output.mp4", Buffer.from(await result.data.arrayBuffer()));
}
For custom polling logic, you can manually control the submit/poll/result flow:
// Submit job
const job = await client.queue.submit({
  model: models.video("lucy-pro-t2v"),
  prompt: "A serene lake at sunset",
});

console.log(`Job ID: ${job.job_id}`);

// Poll for status
while (true) {
  const status = await client.queue.status(job.job_id);
  console.log(`Status: ${status.status}`);

  if (status.status === "completed") {
    const result = await client.queue.result(job.job_id);
    writeFileSync("output.mp4", Buffer.from(await result.data.arrayBuffer()));
    break;
  } else if (status.status === "failed") {
    console.error("Job failed");
    break;
  }

  await new Promise(r => setTimeout(r, 2000));
}

JavaScript Queue API Reference

Full documentation for the JavaScript Queue API

​
Python SDK

The Python SDK now uses client.queue instead of client.generate for video generation.

​
Before

import asyncio
from decart import DecartClient, models

async def generate():
    async with DecartClient(api_key="your-api-key") as client:
        # Synchronous - blocks until video is ready
        video = await client.generate({
            "model": models.video("lucy-pro-t2v"),
            "prompt": "A serene lake at sunset",
        })

        with open("output.mp4", "wb") as f:
            f.write(video)

asyncio.run(generate())

​
After

import asyncio
from decart import DecartClient, models

async def generate():
    async with DecartClient(api_key="your-api-key") as client:
        # Asynchronous - submit and poll for completion
        result = await client.queue.submit_and_poll({
            "model": models.video("lucy-pro-t2v"),
            "prompt": "A serene lake at sunset",
            "on_status_change": lambda job: print(f"Status: {job.status}"),
        })

        if result.status == "completed":
            with open("output.mp4", "wb") as f:
                f.write(result.data)

asyncio.run(generate())
For custom polling logic, you can manually control the submit/poll/result flow:
import asyncio

# Submit job
job = await client.queue.submit({
    "model": models.video("lucy-pro-t2v"),
    "prompt": "A serene lake at sunset",
})

print(f"Job ID: {job.job_id}")

# Poll for status
while True:
    status = await client.queue.status(job.job_id)
    print(f"Status: {status.status}")

    if status.status == "completed":
        result = await client.queue.result(job.job_id)
        with open("output.mp4", "wb") as f:
            f.write(result.data)
        break
    elif status.status == "failed":
        print("Job failed")
        break

    await asyncio.sleep(2)

Python Queue API Reference

Full documentation for the Python Queue API

​
HTTP / REST API

The REST API now uses a three-step flow: submit, poll, and retrieve.

​
Before

# Single request - blocks until complete (could timeout on long generations)
curl -X POST https://api.decart.ai/v1/generate/lucy-pro-t2v \
  -H "X-API-KEY: $DECART_API_KEY" \
  -F "prompt=A serene lake at sunset" \
  --output output.mp4

​
After

# Step 1: Submit job
JOB_ID=$(curl -s -X POST https://api.decart.ai/v1/jobs/lucy-pro-t2v \
  -H "X-API-KEY: $DECART_API_KEY" \
  -F "prompt=A serene lake at sunset" | jq -r '.job_id')

echo "Job submitted: $JOB_ID"

# Step 2: Poll for status
while true; do
  STATUS=$(curl -s -H "X-API-KEY: $DECART_API_KEY" \
    https://api.decart.ai/v1/jobs/$JOB_ID | jq -r '.status')
  echo "Status: $STATUS"
  [ "$STATUS" = "completed" ] && break
  [ "$STATUS" = "failed" ] && exit 1
  sleep 2
done

# Step 3: Download result
curl -H "X-API-KEY: $DECART_API_KEY" \
  https://api.decart.ai/v1/jobs/$JOB_ID/content --output output.mp4

​
Endpoint mapping

Old EndpointNew Endpoint
POST /v1/generate/lucy-pro-t2vPOST /v1/jobs/lucy-pro-t2v
POST /v1/generate/lucy-clipPOST /v1/jobs/lucy-clip
lucy-clip is now a previous-generation model. For new projects, use lucy-2.1 instead.

​
New endpoints for job management

EndpointDescription
GET /v1/jobs/{job_id}Get job status
GET /v1/jobs/{job_id}/contentDownload completed video

​
Key Differences

​
Error handling

The Queue API provides more granular error information through job status: 
const result = await client.queue.submitAndPoll({
  model: models.video("lucy-pro-t2v"),
  prompt: "A serene lake at sunset",
});

if (result.status === "failed") {
  console.error(`Generation failed: ${result.error}`);
}

​
Progress tracking

Monitor job progress with status callbacks: 
const result = await client.queue.submitAndPoll({
  model: models.video("lucy-pro-t2v"),
  prompt: "A serene lake at sunset",
  onStatusChange: (job) => {
    // Called when status changes: pending -> processing -> completed
    updateProgressUI(job.status);
  },
});

​
FAQ

The old synchronous endpoints for video generation are deprecated. Image generation still uses /v1/generate/.
Yes, make sure you’re using the latest version of the SDK:
  • JavaScript: npm install @decartai/sdk@latest
  • Python: pip install decart --upgrade
Image generation continues to use the synchronous Process API (client.process in SDKs, /v1/generate/ for REST). Only video generation has moved to the Queue API.