MiniMax · Video

CF Super-resNEW

📌 What is this：CF super-resolution workflows: output 2K / 4K at the chosen ratio for higher quality. Three values — cf-multi-reference, cf-mj and cf-fl2v — each taking the same inputs as its standard counterpart, with the resolution tier switched to 2K / 4K.

💡 When to use：Use when you need higher-quality (2K / 4K) output. Note: CF workflows only accept resolution=2K/4K (480P/768P/1080P returns 400) and cost more than the standard tiers (2K=30, 4K=60 credits/sec, see billing).

🔗 Response format：The query response follows the OpenAI video-task format: a flat top-level structure (no {code,msg,data} wrapper), lowercase status queued / running / success / failed, success returns video_url, failure returns {"error":{"code","message"}}; video_url is our CDN direct link, ready to download/play.

Endpoints

Usage	Method	Path
Submit task	POST	/v1/videos
Query Result	GET	/v1/videos/{taskId}

⏱ Recommended polling interval：Poll GET /v1/videos/{taskId} every 5s until status = success / failed.

Workflow values

The 3 values share this page’s resolution tiers (2K/4K) and pricing; materials and duration follow their standard counterparts.

workflow_id	Usage	Materials	Duration (sec)	Resolution tiers
cf-multi-reference	Super-res multi-image reference	image_urls <=9 · ref videos <=3 · audio <=3	4~15	2K / 4K
cf-mj	Super-res MJ-style reference	image_urls <=9 · ref videos <=3 · audio <=3	4~15	2K / 4K
cf-fl2v	Super-res first/last-frame transition	first_image (required) + last_image (optional); image_urls / ref videos / audio not accepted	4~10	2K / 4K

⚠ CF values cannot be inferred from inputs — pass workflow_id explicitly. Params marked "only for …" below apply to that value alone; sending them elsewhere returns 400 and nothing is generated.

Request Parameters

Param	Type	Required	Description
model	string	—	Fixed minimax-h3
workflow_id	string	Required	Workflow; 1 of 3 on this page: cf-multi-reference / cf-mj / cf-fl2v. See the table below for what each does; none of these can be inferred from inputs — you must set it explicitly
prompt	string	Required	Required. Text description (the new engine always requires prompt — including image-to-video and first/last-frame, e.g. "gentle camera push-in, soft light")
image_urls	string[]	—	Reference image URLs, up to 9 (alias: images). Only for cf-multi-reference / cf-mj, where it is required; not accepted by cf-fl2v
first_image	string	—	First-frame keyframe image URL (alias: first_frame_image). Only for cf-fl2v, where it is required
last_image	string	—	Last-frame keyframe image URL (optional, alias: last_frame_image). Only for cf-fl2v; must accompany first_image — passing last only returns invalid_request
ratio	string	—	Aspect ratio, 1 of 8: 16:9 / 9:16 / 1:1 / 4:3 / 3:4 / 3:2 / 2:3 / 21:9, default 16:9 (ratio x resolution tier determine the output size; see the size table)
resolution	string	—	Resolution tier (CF super-res workflow): 2K / 4K, default 2K (480P/768P/1080P not accepted); unit price 2K=30, 4K=60 credits/sec, see billing
duration	integer	—	Duration (sec) integer 4-15, default 4 (alias: seconds); cf-fl2v caps at 10 seconds
reference_videos	string[]	—	Reference video URLs, up to 3, as motion/style reference (alias: reference_video). Only for cf-multi-reference / cf-mj
audio_urls	string[]	—	Audio URLs, up to 3, for audio-guided generation (alias: reference_audios). Only for cf-multi-reference / cf-mj
prompt_enhance	boolean	—	Prompt enhancement (optional, boolean); defaults to on if omitted

Request Example

curl -X POST https://api.cqtai.com/v1/videos \
  -H 'Authorization: Bearer <API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
    "model": "minimax-h3",
    "workflow_id": "cf-multi-reference",
    "prompt": "gentle camera push-in, soft light",
    "image_urls": ["https://cdn.novapi.ai/your/frame.png"],
    "ratio": "16:9",
    "resolution": "2K",
    "duration": 8
  }'
# -> 创建响应: { "id":"<task_id>", "task_id":"<task_id>", "object":"video", "model":"minimax-h3", "status":"PROCESSING", "progress":0 }

Response Example

{
  "id": "b976d0f8c1ed4c1c8ef006ea22161bcc",
  "task_id": "b976d0f8c1ed4c1c8ef006ea22161bcc",
  "object": "video",
  "model": "minimax-h3",
  "status": "success",
  "progress": 100,
  "video_url": "https://cdn.novapi.ai/minimax/1786516943631_d6ddaeaa68a4464f9e16938f16b9534b.mp4"
}

Response Fields

Field	Type	Description
id	string	Task ID (opaque), same as task_id; used to poll GET /v1/videos/{task_id}
task_id	string	Task ID (opaque); returned on submit, used for polling
object	string	Object type, always "video"
model	string	Model name, always "minimax-h3"
status	string	Task status (lowercase): queued / running / success / failed
progress	number	Progress 0-100
video_url	string	Result video URL (our CDN direct link); returned when status = success
error	object	Error info {"code","message"}; returned when status = failed

Billing & Credits

Billed per second = credits/sec x duration (sec). CF super-res credits/sec: 2K=30, 4K=60. Example: 2K 6s = 30 x 6 = 180. Auto-refunded on failure.