↓
Rivya AI Docs
Model API Pages

Wan 2.5 Video API Integration

Use Wan 2.5 Video through Rivya Public API v1 with model id wan-2-5-video, supported inputs, parameters, Files API rules, credits, and response examples.

Available via APIText or URL ready; reference modes use Files APIVideo
API model id

wan-2-5-video

Inputs

text, file

Files API

Required for reference modes

Base credits

per_video · 720p_5=60 · 720p_10=120 · 1080p_5=100 · 1080p_10=200 · ⌈total⌉

Capability

Video

Billing

FIXED

Prompt limit

800 characters

Request contract

Send the model id at the top level. Model-specific controls belong in params.

KeyTypeRequiredDefaultDescription
modelstringYeswan-2-5-videoUse the wan-2-5-video API model id.
promptstringYes-Maximum 800 characters for this model.
paramsobjectNo-Model-specific parameter object. Use the rows below for allowed keys.
client_request_idstringNo-Optional client-side id for tracing requests in your system.

Model parameters

KeyTypeRequiredDefaultRangeOptionsDescription
resolutionselectNo720p-720p, 1080pResolution
durationselectNo5-5, 10Duration
aspect_ratioselectNo16:9-16:9, 9:16, 1:1Aspect ratio
enable_prompt_expansionselectNofalse-false, trueBecause Wan 2.5 is for short clips that are already fairly directed. When you are comparing variations of the same shot, seed helps you stay closer to a repeatable option, negative prompt helps remove common failure modes, and prompt expansion lets you decide whether to stay literal or let the model elaborate. That combination is useful when the clip is only 5 or 10 seconds, but the direction is already specific.
seednumberNo-min 0 / max 2147483647-Leave it empty for a new random result each time. Reusing the same integer makes it easier to reproduce or fine-tune a previous result. It stays closer only when the prompt and other key settings also remain similar, and it is not a guaranteed 1:1 match.
negative_prompttextNo---Negative prompt

Upload policy

Upload reference files first, then place the returned URL and duration token inside params.referenceMediaItems.

Reference rule

Reference image: Upload up to 1 image file for image-to-video mode.

Max files

1

Accepted file kinds

image

Duration token

Video and audio references should carry durationToken from /api/v1/files when duration verification is required.

kindMax sizeMIME types
image10 MBimage/jpeg, image/png, image/webp

Minimal request

{
  "model": "wan-2-5-video",
  "prompt": "A cinematic product reveal with smooth camera movement",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": "false",
    "seed": 0,
    "negative_prompt": "Optional exclusions or failure modes to avoid."
  }
}

Reference-file request

{
  "model": "wan-2-5-video",
  "prompt": "A cinematic product reveal with smooth camera movement",
  "params": {
    "resolution": "720p",
    "duration": "5",
    "aspect_ratio": "16:9",
    "enable_prompt_expansion": "false",
    "seed": 0,
    "negative_prompt": "Optional exclusions or failure modes to avoid.",
    "referenceMediaItems": [
      {
        "url": "https://cdn.example.com/reference-image.png",
        "kind": "image",
        "name": "reference-image.png",
        "mimeType": "image/png"
      }
    ]
  }
}

Create response

The create endpoint returns a public task id. Poll the status endpoint until the task succeeds or fails.

{
  "id": "task_wan_2_5_video_example",
  "status": "queued",
  "model": "wan-2-5-video",
  "reserved_credits": 60,
  "final_credits": 0,
  "settlement_status": "RESERVED",
  "created_at": "2026-05-11T00:00:00.000Z",
  "updated_at": "2026-05-11T00:00:00.000Z",
  "result": null,
  "error": null
}

Common errors

validation_failed, insufficient_credits, idempotency_conflict, rate_limited, not_found

Some modes require Files API reference uploads.