Video generations API · loopling

Overview

Video generation is asynchronous. You submit a request and receive a generation id at once; the clip renders in the background; you poll until it is succeeded and then read a signed download link.

Models: seedance-2.5 (4–30 s, up to 1080p), seedance-2.0 (4–15 s, up to 1080p) and seedance-2.0-fast (4–15 s, up to 720p). Rates are on Billing & Ink; a 5-second 1080p Seedance 2.5 clip is 284 Ink.

Ink is reserved when the request is accepted, for the requested duration at the requested resolution, and settled to the duration the vendor reports (never more than requested). A failed generation refunds the whole reservation. At most 2 generations run at once per account; results are kept for 7 days.

Submit

POST /v1/video/generations with a JSON body of up to 64 KiB. The response is 202 Accepted:

curl

curl https://loopling.ai/v1/video/generations \
  -H "Authorization: Bearer $LOOPLING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "duration": 5
  }'

Node

const res = await fetch('https://loopling.ai/v1/video/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.LOOPLING_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'seedance-2.5',
    prompt: 'A paper lantern drifting over a night harbour, slow dolly in',
    aspect_ratio: '16:9',
    resolution: '1080p',
    duration: 5,
  }),
})
const generation = await res.json() // { id: 'vgen_…', status: 'queued', ink_reserved, … }

Python

import os, requests

res = requests.post(
    "https://loopling.ai/v1/video/generations",
    headers={"Authorization": f"Bearer {os.environ['LOOPLING_API_KEY']}"},
    json={
        "model": "seedance-2.5",
        "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
        "aspect_ratio": "16:9",
        "resolution": "1080p",
        "duration": 5,
    },
)
generation = res.json()  # {"id": "vgen_…", "status": "queued", "ink_reserved": …}

{
  "id": "vgen_01J9X6K3M8Q2",
  "object": "video.generation",
  "status": "queued",
  "model": "seedance-2.5",
  "created_at": "2026-09-17T08:12:44Z",
  "ink_reserved": 284,
  "usd_payg_reserved": 2.84,
  "request": {
    "model": "seedance-2.5",
    "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "duration": 5,
    "generate_audio": true
  }
}

request is the normalised request as accepted — defaults filled in, reference lists in the order they were given, metadata echoed inside it. ink_reserved is the hold; usd_payg_reserved is the same figure at $1 = 100 Ink. Rendering typically takes one to a few minutes depending on duration and resolution.

Request schema

Reference limits, per generation: seedance-2.5 takes up to 50 references — 30 images, 10 videos, 10 audio; seedance-2.0 and seedance-2.0-fast take up to 12 — 9 images, 3 videos, 3 audio. A list longer than its per-kind cap answers too_many; a set that breaks the model's total or its audio-anchor rule answers reference_limit. Frames (first_frame_url / last_frame_url) and reference_* inputs are mutually exclusive on Seedance — combining them answers conflicting_references.

Every URL must be https:// without embedded credentials, at most 2,048 characters, and publicly fetchable at submit time (invalid_url); Loopling reads it once, on your behalf, and does not keep the source.

An optional Idempotency-Key header makes the submit safe to retry — see Idempotency.

Poll

GET /v1/video/generations/{id} returns the generation's current state. Poll every few seconds; the per-key rate limit applies to polling like any other call, so five-second intervals are a sensible floor.

curl

curl https://loopling.ai/v1/video/generations/vgen_01J9X6K3M8Q2 \
  -H "Authorization: Bearer $LOOPLING_API_KEY"

Node

const headers = { Authorization: `Bearer ${process.env.LOOPLING_API_KEY}` }

async function waitForVideo(id) {
  for (;;) {
    const res = await fetch(`https://loopling.ai/v1/video/generations/${id}`, { headers })
    const gen = await res.json()
    if (gen.status === 'succeeded') return gen.video // { url, expires_at, duration_seconds, … }
    if (gen.status === 'failed') throw new Error(gen.error?.message ?? 'generation failed')
    await new Promise((r) => setTimeout(r, 5000))
  }
}

const video = await waitForVideo(generation.id)
// video.url is signed and valid for 15 minutes; read the generation again for a fresh one.

Python

import time

headers = {"Authorization": f"Bearer {os.environ['LOOPLING_API_KEY']}"}

def wait_for_video(generation_id: str) -> dict:
    while True:
        gen = requests.get(f"https://loopling.ai/v1/video/generations/{generation_id}", headers=headers).json()
        if gen["status"] == "succeeded":
            return gen["video"]  # {"url": …, "expires_at": …, "duration_seconds": …}
        if gen["status"] == "failed":
            raise RuntimeError(gen.get("error", {}).get("message", "generation failed"))
        time.sleep(5)

video = wait_for_video(generation["id"])
# video["url"] is signed and valid for 15 minutes; read the generation again for a fresh one.

Response schema

{
  "id": "vgen_01J9X6K3M8Q2",
  "object": "video.generation",
  "status": "succeeded",
  "model": "seedance-2.5",
  "created_at": "2026-09-17T08:12:44Z",
  "completed_at": "2026-09-17T08:15:02Z",
  "video": {
    "url": "https://media.loopling.ai/…?sig=…",
    "expires_at": "2026-09-17T08:30:02Z",
    "content_type": "video/mp4",
    "duration_seconds": 5,
    "resolution": "1080p",
    "aspect_ratio": "16:9",
    "size_bytes": 8421376
  },
  "seed": 1842273,
  "ink_reserved": 284,
  "usd_payg_reserved": 2.84,
  "ink_charged": 284,
  "usd_payg_charged": 2.84,
  "request": {
    "model": "seedance-2.5",
    "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "duration": 5,
    "generate_audio": true
  }
}

Ownership follows the key's account: a generation another account created answers 404 generation_not_found.

Download

GET /v1/video/generations/{id}/content answers 302 to a fresh signed URL for the MP4 — convenient for curl -L and for clients that would rather not parse JSON to download. Before the generation finishes it answers 409 with code: "generation_not_ready"; after the 7-day retention it answers 410 with code: "result_expired"; a failed generation answers 404 result_unavailable.

curl

# 302 to a fresh signed URL; -L follows it and -o saves the MP4.
curl -L https://loopling.ai/v1/video/generations/vgen_01J9X6K3M8Q2/content \
  -H "Authorization: Bearer $LOOPLING_API_KEY" \
  -o lantern.mp4

Node

const res = await fetch(`https://loopling.ai/v1/video/generations/${generation.id}/content`, {
  headers: { Authorization: `Bearer ${process.env.LOOPLING_API_KEY}` },
  redirect: 'follow',
})
await fs.promises.writeFile('lantern.mp4', Buffer.from(await res.arrayBuffer()))

Python

res = requests.get(
    f"https://loopling.ai/v1/video/generations/{generation['id']}/content",
    headers={"Authorization": f"Bearer {os.environ['LOOPLING_API_KEY']}"},
    allow_redirects=True,
)
open("lantern.mp4", "wb").write(res.content)

Signed links are valid for 15 minutes and are not authenticated beyond the signature — do not publish them; fetch the bytes and serve them yourself.

Idempotency

Send an Idempotency-Key header with the submit: 1–128 characters of letters, digits, ., _, : or -, unique per intent (anything else answers 400 invalid_idempotency_key). A repeated submit with the same key on the same API key within 24 hours returns the original 202 body — one reservation, one vendor task — with the header Idempotent-Replayed: true, instead of starting a second render. Use a new key for a new request.

Idempotency-Key: order-8812-hero-shot

Errors

Beyond the shared error types, the video endpoints answer these code values. Everything under 400 names the field in param.

A generation that fails after acceptance carries the reason in error on the poll response, with ink_charged: 0:

{
  "id": "vgen_01J9X6K3M8Q2",
  "object": "video.generation",
  "status": "failed",
  "model": "seedance-2.5",
  "created_at": "2026-09-17T08:12:44Z",
  "completed_at": "2026-09-17T08:13:10Z",
  "ink_reserved": 284,
  "usd_payg_reserved": 2.84,
  "ink_charged": 0,
  "usd_payg_charged": 0,
  "request": { "model": "seedance-2.5", "prompt": "…", "aspect_ratio": "16:9", "resolution": "1080p", "duration": 5, "generate_audio": true },
  "error": { "code": "provider_failed", "message": "The vendor did not complete the generation." }
}

Examples

A complete submit-and-poll loop in Node and Python, and the same in curl:

curl

curl https://loopling.ai/v1/video/generations \
  -H "Authorization: Bearer $LOOPLING_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "seedance-2.5",
    "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
    "aspect_ratio": "16:9",
    "resolution": "1080p",
    "duration": 5
  }'

Node

const res = await fetch('https://loopling.ai/v1/video/generations', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.LOOPLING_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'seedance-2.5',
    prompt: 'A paper lantern drifting over a night harbour, slow dolly in',
    aspect_ratio: '16:9',
    resolution: '1080p',
    duration: 5,
  }),
})
const generation = await res.json() // { id: 'vgen_…', status: 'queued', ink_reserved, … }

const headers = { Authorization: `Bearer ${process.env.LOOPLING_API_KEY}` }

async function waitForVideo(id) {
  for (;;) {
    const res = await fetch(`https://loopling.ai/v1/video/generations/${id}`, { headers })
    const gen = await res.json()
    if (gen.status === 'succeeded') return gen.video // { url, expires_at, duration_seconds, … }
    if (gen.status === 'failed') throw new Error(gen.error?.message ?? 'generation failed')
    await new Promise((r) => setTimeout(r, 5000))
  }
}

const video = await waitForVideo(generation.id)
// video.url is signed and valid for 15 minutes; read the generation again for a fresh one.

Python

import os, requests

res = requests.post(
    "https://loopling.ai/v1/video/generations",
    headers={"Authorization": f"Bearer {os.environ['LOOPLING_API_KEY']}"},
    json={
        "model": "seedance-2.5",
        "prompt": "A paper lantern drifting over a night harbour, slow dolly in",
        "aspect_ratio": "16:9",
        "resolution": "1080p",
        "duration": 5,
    },
)
generation = res.json()  # {"id": "vgen_…", "status": "queued", "ink_reserved": …}

import time

headers = {"Authorization": f"Bearer {os.environ['LOOPLING_API_KEY']}"}

def wait_for_video(generation_id: str) -> dict:
    while True:
        gen = requests.get(f"https://loopling.ai/v1/video/generations/{generation_id}", headers=headers).json()
        if gen["status"] == "succeeded":
            return gen["video"]  # {"url": …, "expires_at": …, "duration_seconds": …}
        if gen["status"] == "failed":
            raise RuntimeError(gen.get("error", {}).get("message", "generation failed"))
        time.sleep(5)

video = wait_for_video(generation["id"])
# video["url"] is signed and valid for 15 minutes; read the generation again for a fresh one.

OpenAI SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://loopling.ai/v1",
    api_key=os.environ["LOOPLING_API_KEY"],
)

response = client.responses.create(
    model="gpt-6-astra",
    instructions="You are a concise studio assistant.",
    input="Give me three shot ideas for a night harbour scene.",
    max_output_tokens=2048,
)
print(response.output_text)

Anthropic SDK

import anthropic

# auth_token sends "Authorization: Bearer …", which is what Loopling reads.
client = anthropic.Anthropic(
    base_url="https://loopling.ai/v1",
    auth_token=os.environ["LOOPLING_API_KEY"],
)

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Give me three shot ideas for a night harbour scene."}],
)
print(message.content[0].text)

loopling.ai · grows with you, grows itself

hello@loopling.ai · community · pricing · Enterprise · API · privacy · terms