API reference / Queue

Submit

llms-full.txt

POSThttps://api.minicut.ai/v1/queue/{model_id}

Starts a job and answers at once with a request id. Unknown fields are refused with 422.

Path

model_idstringrequired

Model id, for example seedance-2.5

Query

webhook_urlstring, url

Where we POST the result when the job ends. https, and public addresses only.

Headers

Idempotency-Keystring

Send the same key again and you get the same request back, with no second charge. The same key with a different body is 409.

X-Quote-Idstring

Pay the price from POST /v1/quote for this body. Expires after 15 minutes.

Body: wan-2.2

An older, cheaper Wan for a shot where nothing has to be perfect.

promptstringrequired

What to make, in plain words.

num_framesinteger17 to 161

Number of frames to make.

frames_per_secondinteger4 to 60

negative_promptstring

What to keep out of the result.

resolutionstring

Output size. Higher is sharper, slower and costs more.

480p580p720p

aspect_ratiostring

Shape of the result, for example 16:9 or 9:16.

auto16:99:161:1

num_inference_stepsinteger2 to 40

More steps can add detail and take longer.

enable_prompt_expansionboolean

Let the model add detail to a short prompt.

truefalse

accelerationstring

noneregular

guidance_scalenumber1 to 10

How closely to follow the prompt. Higher follows it more literally.

guidance_scale_2number1 to 10

shiftnumber1 to 10

interpolator_modelstring

nonefilmrife

num_interpolated_framesinteger0 to 4

adjust_fps_for_interpolationboolean

truefalse

video_qualitystring

lowmediumhighmaximum

video_write_modestring

fastbalancedsmall

enable_output_safety_checkerany

end_image_urlstring, url

A picture for the last frame.

image_urlstring, url

A picture to start from. We fetch it and keep a copy for the job.

seedinteger

The same seed with the same settings gives a similar result. Leave it out for a random one.

Response 200

request_idstring

statusstring

queue_positioninteger

Your jobs ahead of this one in line. 0 is next to start

status_urlstring, url

response_urlstring, url

cancel_urlstring, url

pricestring

The price of this request, 6 decimal places, in the currency named by the `currency` field

currencystring

The currency of every amount on this object and the items inside it. Always USD

curl -X POST "https://api.minicut.ai/v1/queue/wan-2.2" \
  -H "Authorization: Key $MINIAPI_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"a red fox runs through snow at dawn","resolution":"720p"}'

Response 200

{
  "request_id": "0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "status": "IN_QUEUE",
  "queue_position": 0,
  "status_url": "https://api.minicut.ai/v1/queue/wan-2.2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/status",
  "response_url": "https://api.minicut.ai/v1/queue/wan-2.2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd",
  "cancel_url": "https://api.minicut.ai/v1/queue/wan-2.2/requests/0192f3a4-5b6c-7d8e-9f01-23456789abcd/cancel",
  "price": "1.750000",
  "currency": "USD"
}

400invalid_json The body is not JSON

400invalid_webhook_url webhook_url is not https, or points at a private address

401missing_api_key No Authorization header

401invalid_api_key Wrong, unknown or revoked key

402insufficient_balance Your balance is under the price

403account_frozen The account is frozen

409idempotency_conflict Same Idempotency-Key, different body

410quote_expired The quote is older than 15 minutes or for another body

422validation_error A field fails the model's settings

422input_fetch_failed An input URL could not be fetched

422content_refused The content check refused it

429rate_limited Too many requests; wait for Retry-After

500internal_error Our side; try again

503model_unavailable Cannot take jobs right now; try again in 60 s