Use Wan 2.6 T2V with Comfy Router

Call wan/wan2.6-t2v through Comfy Router: endpoint, request shape and the response Router returns.

API Reference for wan/wan2.6-t2v, served by Comfy Router from Wan.

Quick start

Create a key at platform.comfy.org/profile/api-keys and export it as COMFY_API_KEY. The Python and TypeScript snippets use the Comfy SDKs (pip install comfy-sdk, npm install @comfyorg/sdk); the cURL snippet is the same call over raw HTTP.

Model ID: wan/wan2.6-t2v

Endpoint: POST https://api.comfy.org/v2/models/wan/wan2.6-t2v

Python

from comfy_sdk import Comfy

# Reads COMFY_API_KEY from the environment. Each call sends a fresh
# Idempotency-Key and waits up to 10 minutes for the finished result.
with Comfy() as client:
    result = client.models.run(
        "wan/wan2.6-t2v",
        {
            # Request fields are the provider's own — see Input below.
        },
    )

print(result)

Schema

Input

input · object · required

Enter basic information, such as prompt words, etc.

input.audio_url · string

Audio file download URL. Supported formats: mp3 and wav. Cannot be used with reference_video_urls.

input.img_url · string

First frame image URL or Base64 encoded data. Required for I2V models. Image formats: JPEG, JPG, PNG, BMP, WEBP. Resolution: 360-2000 pixels. File size: max 10MB.

input.media · object[]

Media asset list for wan2.7 and wan3.0 models. Specifies reference materials (image, audio, video) for video generation. Each element contains a type and url field. Supported type values vary by model:

• wan2.7-i2v: first_frame, last_frame, driving_audio, first_clip
• wan2.7-r2v: reference_image, reference_video
• wan2.7-videoedit: video, reference_image
• wan3.0-video: first_frame (max 1), last_frame (max 1), reference_image (max 10), reference_video (max 5 clips, total duration <= 15s), reference_audio (max 5 clips, total duration <= 15s), file (max 1, cannot be used with link), link (max 1, cannot be used with file). The reference_*/file/link types and first_frame/last_frame types are mutually exclusive within the same request. The array order defines the reference order of assets in the prompt (Image 1, Video 1, Audio 1, …).

input.media[].type · string · required

Media asset type

Possible values: first_frame, last_frame, driving_audio, first_clip, reference_image, reference_video, reference_audio, video, file, link

input.media[].url · string · required

URL of the media file (public HTTP/HTTPS URL or OSS temporary URL)

input.negative_prompt · string

Reverse prompt words are used to describe content that you do not want to see in the video screen

input.prompt · string

Text prompt words. Support Chinese and English, length not exceeding 800 characters (up to 20,000 characters for wan3.0-video; content exceeding the limit is truncated). For wan2.6-r2v with multiple reference videos, use ‘character1’, ‘character2’, etc. to refer to subjects in the order of reference videos. Example: “Character1 sings on the roadside, Character2 dances beside it” For wan3.0-video reference mode, use ‘Image 1’, ‘Video 1’, ‘Audio 1’, etc. to refer to media assets in the corresponding order within the media array.

input.reference_video_urls · string[]

Reference video URLs for wan2.6-r2v model only. Array of 1-3 video URLs. Input restrictions:

• Format: mp4, mov
• Quantity: 1-3 videos
• Single video length: 2-30 seconds
• Single file size: max 30MB
• Cannot be used with audio_url Reference duration: Single video max 5s, two videos max 2.5s each, three videos proportionally less. Billing: Based on actual reference duration used.

input.template · string

Video effect template name. Optional. Currently supported: squish, flying, carousel. When used, prompt parameter is ignored.

model · string

The ID of the model to call. NOT constrained on this component: Comfy Router fills it from the {model} path segment of POST /v2/models/wan/{model}, so a Router caller omits it. A direct v1 call to POST /proxy/wan/api/v1/services/aigc/video-generation/video-synthesis MUST supply it, and the enum of accepted spellings lives on that operation’s own component, WanVideoGenerationRequest.

parameters · object

Video processing parameters

parameters.audio · boolean · default: "true"

Whether to add audio to the video

parameters.audio_setting · string · default: "\"auto\""

Video audio setting for wan2.7-videoedit model.

• auto (default): Model intelligently judges based on prompt content

• origin: Forcefully preserve the original audio from the input video

  Possible values: auto, origin

parameters.duration · integer · default: "5"

The duration of the video generated, in seconds:

• wan2.5 models: 5 or 10 seconds

• wan2.6-t2v, wan2.6-i2v: 5, 10, or 15 seconds

• wan2.6-r2v: 5 or 10 seconds only (no 15s support)

• wan2.7-i2v, wan2.7-t2v: integer in [2, 15]

• wan2.7-r2v, wan2.7-videoedit: integer in [2, 10]

• wan3.0-video: integer in [2, 30] without video input; with video input the total input video duration + output video duration must not exceed 30 seconds; -1 enables smart duration mode where the model picks a suitable duration

  Range: -1 to 30

parameters.prompt_extend · boolean · default: "true"

Is it enabled prompt intelligent rewriting. Default is true

parameters.ratio · string

Aspect ratio of the generated video. For wan2.7 and wan3.0 models only. For wan2.7 models, defaults based on the resolution tier if not provided. For wan3.0-video, adaptive (the default) automatically recommends a suitable aspect ratio based on the input media proportions and intent.

Possible values: adaptive, 16:9, 9:16, 1:1, 4:3, 3:4

parameters.resolution · string

Resolution level. Supported values vary by model:

• wan2.5-i2v-preview: 480P, 720P, 1080P

• wan2.6-i2v: 720P, 1080P only (no 480P support)

• wan2.7 models (i2v, t2v, r2v, videoedit): 720P, 1080P (default 1080P)

• wan3.0-video, wan3.0-video-prime: 480P, 720P, 1080P (upstream default 1080P) This proxy rejects video generation requests that provide neither resolution nor size, because the resolution tier selects the billing rate.

  Possible values: 480P, 720P, 1080P

parameters.seed · integer

Random number seed, used to control the randomness of the model generated content

Range: 0 to 2147483647

parameters.shot_type · string · default: "\"single\""

Intelligent multi-lens control. Only active when prompt_extend is enabled. For wan2.6 and wan2.7-r2v models.

• single: Single-shot video (default)

• multi: Multi-shot video

  Possible values: multi, single

parameters.size · string

Video resolution in format widthheight. Supported resolutions vary by model: For wan2.5 T2V: 480P (480832, 832480, 624624), 720P, 1080P sizes For wan2.6 T2V/R2V (no 480P): 720P: 1280720, 7201280, 960960, 1088832, 8321088 1080P: 19201080, 10801920, 14401440, 16321248, 12481632

parameters.watermark · boolean · default: "false"

Whether to add a watermark logo, the watermark is located in the lower right corner

Generated from the schema Router serves at GET /v2/models/wan/wan2.6-t2v/openapi.json, the same document it validates a call against before the request reaches the provider.

Output

output · object · required

output.actual_prompt · string

Actual prompt after intelligent rewriting (for video tasks)

output.check_audio · string

Audio URL for I2V tasks with audio generation

output.code · string

The error code for the failed request (not returned if request is successful)

output.end_time · string

Task completion time

output.message · string

Detailed information about the failed request (not returned if request is successful)

output.orig_prompt · string

Original input prompt (for video tasks)

output.results · object[]

List of task results for image generation tasks

output.results[].actual_prompt · string

Actual prompt after intelligent rewriting (if enabled)

output.results[].code · string

Image error code (returned when some tasks fail)

output.results[].message · string

Image error information (returned when some tasks fail)

output.results[].orig_prompt · string

Original input prompt

output.results[].url · string

Generated image URL address

output.scheduled_time · string

Task execution time

output.submit_time · string

Task submission time

output.task_id · string · required

Task ID

output.task_metrics · object

Task result statistics for image generation tasks

output.task_metrics.FAILED · integer

Number of failed tasks

output.task_metrics.SUCCEEDED · integer

Number of successful tasks

output.task_metrics.TOTAL · integer

Total number of tasks

output.task_status · string · required

Task status

Possible values: PENDING, RUNNING, SUCCEEDED, FAILED, CANCELED, UNKNOWN

output.video_url · string

Video URL for completed video generation tasks. Link validity period 24 hours

request_id · string · required

Unique request identifier

usage · object

Output information statistics. Only successful results are counted

usage.SR · integer

Video resolution level (I2V and wan3.0-video tasks)

usage.duration · number

Duration of generated video in seconds (I2V and wan3.0-video tasks)

usage.fps · integer

Frame rate of the generated video (wan3.0-video tasks)

usage.image_count · integer

Number of generated images (T2I tasks)

usage.input_video_duration · number

Duration of the input video in seconds, 0.0 when no video input (wan3.0-video tasks)

usage.output_video_duration · number

Duration of the output video in seconds (wan3.0-video tasks)

usage.ratio · string

Aspect ratio of the generated video, e.g. 16:9 (wan3.0-video tasks)

usage.size · string

Image resolution (T2I tasks)

usage.video_count · integer

Number of generated videos (T2V tasks)

usage.video_duration · number

Duration of generated video in seconds (T2V tasks)

usage.video_ratio · string

Video resolution ratio (T2V tasks)

code · string

Error code for a failed request, reported at the ROOT of the envelope rather than under output (not returned if the request succeeded).

message · string

Detailed information about a failed request, reported at the ROOT of the envelope rather than under output (not returned if the request succeeded). Read this before falling back to output.message.

Examples

Output

{
  "output": {
    "actual_prompt": "a single red maple leaf falling onto still water, slow motion, shallow depth of field",
    "end_time": "2027-01-01T00:01:04.000Z",
    "orig_prompt": "a single red maple leaf falling onto still water",
    "scheduled_time": "2027-01-01T00:00:01.000Z",
    "submit_time": "2027-01-01T00:00:00.000Z",
    "task_id": "0385dc79-5ff8-4d82-bcb6-7c1a9f2e4d60",
    "task_status": "SUCCEEDED",
    "video_url": "https://example.invalid/wan/wan2.6-t2v/generated.mp4"
  },
  "request_id": "7574ee8f-38a3-4b1e-9280-11c33ab46e51",
  "usage": {
    "video_count": 1,
    "video_duration": 5,
    "video_ratio": "1920*1080"
  }
}

Before you ship

The snippets above are the shortest working call. Three things are the same for every model and are documented once on the Comfy Router headers page: send an Idempotency-Key on every paid call and reuse it when you retry, expect the connection to be held up to Router’s 10 minute deadline, and keep X-Comfy-Request-Id from every response. The SDKs do all three for you; the cURL tab does none of them. On failure, X-Comfy-Error-Type names the bucket, and a 422 means the body failed the model’s schema and was never billed.

Headers

Authentication, idempotency, request IDs, error buckets, retry pacing, spend limits.

Quick Start

Typed error handling in Python and TypeScript, reading the 422, walking the catalog.

Limitations

What Router does not do today, and what to use instead.