80trust / 100

Video Queue

by AiSpace Venice in AI models & inference

x402 APIPassing, checked 4 h ago

Async text-to-video and image-to-video generation on Venice (WAN 3.0, Seedance 2.5, HappyHorse, and more), paid per request in USDC on Base via x402, no API key. Model ids via GET /api/v1/models?type=video. Lifecycle: quote, queue, retrieve, complete (see related routes).

POST
https://x402.aispace.bot/api/v1/video/queue
Price
$0.65
per call in USDC
Uptime
100%
last 30 days
Response time
369 ms
613 ms slowest 5%
Last check
Passed
4 h ago, next any minute now

Run a free test callHow to call it

Reliability

All checks passedSome failedAll failedNot checked

Status and outage history · Atom feed · Watch with other listings

How to call it

POST https://x402.aispace.bot/api/v1/video/queue

Each call costs $0.65 in USDC on Base, paid with the request over x402.

Run a free test callOne unpaid request, the way an agent sends it. You see the payment challenge it gets back. Nothing is charged.

Example request

From the listing.

POST https://x402.aispace.bot/api/v1/video/queue
content-type: application/json

{
  "aspect_ratio": "16:9",
  "duration": "5s",
  "model": "wan-3-0-text-to-video",
  "prompt": "A paper boat sailing down a rain-soaked street, slow motion",
  "resolution": "1080p"
}

Parameters

ParameterTypeRequiredDescription
aspect_ratiostringNoFrame aspect ratio when listed. Seedance 2.x R2V: `adaptive` or `auto` matches the source. Omit on I2V models that list none.
audiostringNoOnly send this when the model lists audio_configurable=true. Mute models (audio:false) reject the field entirely — omit it, do not send audio:false.
consentsobjectNoOptional Seedance consent object. This gateway attaches provider consents on queue when the catalog requires them. bitrate_mode is not in the current Venice swagger — do not send undocumented keys.
durationstringYesClip length from this model's model_spec.constraints.durations. Seedance 2.x R2V: `-1` or `auto` matches the source clip (needs reference_video_urls). MiniMax H3 Max Recast: `Auto` (aliases `auto` / `-1`).
imagestringNoAlias for image_url. Accepted and remapped before the Venice proxy; prefer image_url.
image_urlstringNoSource image (URL or base64) for image-to-video models. Required when model_type is image-to-video. Venice field name is image_url.
modelstringYesVenice video model id. See GET /api/v1/models?type=video (e.g. wan-3-0-text-to-video, seedance-2-5-text-to-video-basic). Confirm duration/resolution on that row before quoting.
negative_promptstringNoOptional. Same max-length rules as prompt (up to 20000 on some models).
omni_reference_task_typestringNoOptional Seedance 2.5 reference-to-video task-type hint (auto|reference|edit|extend). Aliases editing→edit, extension→extend. Not supported on other models.
promptstringYesVideo description / motion prompt. Required on queue. Max length varies by model (default 2500, up to 20000).
resolutionstringNoOutput resolution. When the model lists model_spec.constraints.resolutions, use one of those values.

Example response

The provider's example. We can't check it without paying.

{
  "model": "gemini-omni-flash-1-1-text-to-video",
  "queue_id": "01a057ba-5a5c-711d-9581-d59281f0ef7e"
}

Call it from code

The curl command shows the payment challenge. The JavaScript and Python versions pay and call, and never pay more than $0.65.

curl: see the payment challenge
# bash or zsh: see the payment challenge. Nothing is charged.
curl -sS -g -i -X POST 'https://x402.aispace.bot/api/v1/video/queue' \
  -H 'content-type: application/json' \
  --data-raw '{"aspect_ratio":"16:9","duration":"5s","model":"wan-3-0-text-to-video","prompt":"A paper boat sailing down a rain-soaked street, slow motion","resolution":"1080p"}'

# x402 v2 sends the challenge base64-encoded in the PAYMENT-REQUIRED header (v1 sends it in the body).
# To read the header:
curl -sS -g -o /dev/null -D - -X POST 'https://x402.aispace.bot/api/v1/video/queue' \
  -H 'content-type: application/json' \
  --data-raw '{"aspect_ratio":"16:9","duration":"5s","model":"wan-3-0-text-to-video","prompt":"A paper boat sailing down a rain-soaked street, slow motion","resolution":"1080p"}' \
  | grep -i '^payment-required:' | cut -d' ' -f2 | tr -d '\r' | base64 --decode
JavaScript: pay and call
// npm i @x402/fetch @x402/evm viem
import { wrapFetchWithPayment, x402Client } from "@x402/fetch";
import { registerExactEvmScheme } from "@x402/evm/exact/client";
import { privateKeyToAccount } from "viem/accounts";

// Pays at most $0.65 per call.
const client = new x402Client().setSpendControls({ maxAmountPerPayment: "$0.65" });
registerExactEvmScheme(client, { signer: privateKeyToAccount(process.env.EVM_PRIVATE_KEY) });
const pay = wrapFetchWithPayment(fetch, client);

// Not sure it's safe to pay? ToolVet checks it first for $0.005. Pay for that from a separate
// client: this one is capped at $0.65 per payment. GET https://toolvet.app/api/v1/check?url=https%3A%2F%2Fx402.aispace.bot%2Fapi%2Fv1%2Fvideo%2Fqueue&method=POST
const res = await pay("https://x402.aispace.bot/api/v1/video/queue", {
  method: "POST",
  headers: { "content-type": "application/json" },
  body: JSON.stringify({
    "aspect_ratio": "16:9",
    "duration": "5s",
    "model": "wan-3-0-text-to-video",
    "prompt": "A paper boat sailing down a rain-soaked street, slow motion",
    "resolution": "1080p"
  }),
});
console.log(res.status, await res.text());
Python: pay and call
# pip install "x402[requests,evm]"
import os
from eth_account import Account
from x402 import x402ClientSync
from x402.http.clients import x402_requests
from x402.mechanisms.evm import EthAccountSigner
from x402.mechanisms.evm.exact.register import register_exact_evm_client

# Pays at most $0.65 per call.
client = x402ClientSync().set_spend_controls({"max_amount_per_payment": "$0.65"})
register_exact_evm_client(client, EthAccountSigner(Account.from_key(os.environ["EVM_PRIVATE_KEY"])))

with x402_requests(client) as session:
    res = session.post(
        "https://x402.aispace.bot/api/v1/video/queue",
        json={
            "aspect_ratio": "16:9",
            "duration": "5s",
            "model": "wan-3-0-text-to-video",
            "prompt": "A paper boat sailing down a rain-soaked street, slow motion",
            "resolution": "1080p",
        },
    )
    print(res.status_code, res.text)

Security scan

No findings

We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTimePrice
4 h agoPassed402485 ms$0.65
8 h agoPassed402361 ms$0.65
13 h agoPassed402362 ms$0.65
17 h agoPassed402307 ms$0.65
22 h agoPassed402335 ms$0.65
Show 10 older checks
26 h agoPassed402326 ms$0.65
30 h agoPassed402487 ms$0.65
35 h agoPassed402322 ms$0.65
39 h agoPassed4021.3 s$0.65
43 h agoPassed402399 ms$0.65
47 h agoPassed402403 ms$0.65
2 days agoPassed402388 ms$0.65
2 days agoPassed402366 ms$0.65
3 days agoPassed402341 ms$0.65
3 days agoPassed402346 ms$0.65