popnow
Sign inStart creating

alibaba/wan-2.6/text-to-videoFrom 49 credits for a 5-second clip· Reference to Video

Wan 2.6 is Alibaba's December 2025 Wan release, published here as three APIs: text-to-video, image-to-video and reference-to-video. Text and image start from a written shot or an opening frame and return exactly 5, 10 or 15 seconds with sound; reference-to-video casts subjects from up to three clips into a new scene of 2 to 10 seconds. All three run at 720p or 1080p and carry a shot_type switch between one continuous take and a multi-shot edit.

Call it with the model name alibaba/wan-2.6/text-to-video on POST /jobs/createTask, from 68 credits for a 5-second clip ($0.68). New accounts get 30 free credits to try it in the Playground first.

  • Create Video
  • Image to Video
  • Reference to Video
  • Up to 1080p
  • 2–15s clips
  • Up to 2 reference images
  • 5 aspect ratios
by AlibabaGet API keyWan 2.6 examples and prompts →

Introduction

Wan 2.6 Text to video turns a written shot, or a numbered list of shots, into a clip of exactly 5, 10 or 15 seconds at 720p or 1080p. Only prompt is required. Everything else has a default: 16:9, 720p, five seconds, one continuous take and prompt expansion off. The clip comes back with sound generated alongside the picture, and audio_url can hand it a recorded line or music cue to follow instead.

Choose a Wan 2.6 mode by starting material

What you have at the startMode
a written scene or scriptWan 2.6 Text to video
an approved opening imageWan 2.6 Image to video
separate visual, motion, or sound referencesWan 2.6 Reference to video

Key features

Five shapes at both resolutions

aspect_ratio accepts 16:9, 9:16, 1:1, 4:3 and 3:4, and every shape is available at 720p and at 1080p. Nothing is inherited from an input frame, so the same brief can be rendered as a landscape master and as a vertical cut-down by changing one field. Resolution sets the per-second rate and how long the task takes, which makes the default 720p the natural place to settle a prompt.

One take or a planned sequence

shot_type switches between single, one continuous take, and multi, where the model may cut between several shots inside the same clip. A multi request always runs with prompt expansion on, whatever enable_prompt_expansion says, because the cuts are planned while the brief is expanded. Multi suits a short story with a beat to it; single is the choice when continuity matters more than coverage.

Sound in the same pass

Audio is generated with the picture, so a sentence about sound at the end of the prompt shapes what you hear. When the sound already exists, audio_url takes a WAV or MP3 of 3 to 30 seconds and up to 15 MB, and mouth shapes and movement pace themselves to that file. A longer track is cut to the clip length; with a shorter one, the rest of the clip is silent.

Request parameters

ParameterRequiredDescription
aspect_ratioNoThe shape of the frame: wide, square or tall. 16:9 · 9:16 · 1:1 · 4:3 · 3:4 · Default: 16:9
audio_urlNoThe voice or music track to use.
duration_secondsNoHow long the clip runs. You pay per second. 5 · 10 · 15 · Default: 5
enable_prompt_expansionNoLets the model add detail to a short prompt. Default: false
negative_promptNoThings you don't want to see.
promptYesDescribe the subject, action, camera, light, pacing, and boundaries for the shot.
resolutionNoOutput size. Bigger sizes look sharper and cost more. 720p · 1080p · Default: 720p
seedNoReuse the same number to get a repeatable result. ≥ 0 · ≤ 2147483647
shot_typeNoSingle continuous shot, or a multi-shot edit. single · multi · Default: single

Pricing

Prices are in credits, the same credits you use on the website (1 credit = $0.01). The hold is taken when the task is accepted and settled to the actual charge when it finishes; failed tasks are refunded.

OptionCredits per second≈ USD
resolution 720p13.5$0.14
resolution 1080p20.25$0.20

Each task is rounded up to whole credits, so one run at the lowest tier costs 68 credits for a 5-second clip ($0.68).

For an exact number before you run, send the same body to POST /jobs/quote.

Use cases

An atmospheric single shot with written sound

The published harbour example shows the single-take pattern. A fisherman in a yellow oilskin coils a wet rope, looks up at a passing ferry and raises a hand, seen through one slow dolly from behind a stack of crates. The prompt closes with an audio line, so steady rain, a long ferry horn and the creak of the rope sit under the picture without a separate track. It runs at 16:9, five seconds, 720p.

A vertical micro-story for social feeds

The bakery example asks for three numbered shots in a 9:16 clip of ten seconds at 1080p: the shutter rolling up at dawn, floured hands shaping a loaf, then the oven door glowing as a tray goes in. shot_type is multi, so each numbered line gets its own cut, and a fixed seed keeps the draw steady while the wording is refined.

Look development before anything is shot

A written brief is enough to test setting, light and pacing for a scene that does not exist yet. It will not hold a specific face or product between runs. Once a person or a package has to stay recognisable, create the frame first and move the job to image-to-video, where the opening image fixes the appearance.

Prompt guide & pro tips

Write a single take in four parts

For single, name the subject, give one action, give one camera move, then add light and a line about sound. The harbour prompt follows that order, which is why its result is easy to judge: either the rope, the glance and the raised hand all happen while the dolly stays behind the crates, or they do not.

Late evening on a rain-soaked harbour quay. A fisherman in a yellow oilskin coils a wet rope, looks up at a passing ferry and raises a hand. Slow dolly from behind a stack of crates, sodium lights reflecting in the puddles. Audio: steady rain, a long ferry horn, the rope creaking.

Number the shots for multi

For multi, start each line with "Shot 1:", "Shot 2:" and so on, and give every line its own framing and subject. Keep one event per line: once a line describes two events, the boundary between cuts is no longer yours to set. Multi-shot edits need the longer lengths to breathe, so choose 10 or 15 seconds.

Keep exclusions out of the main brief

Captions, logos, extra people or a colour you keep getting belong in negative_prompt, which holds up to 500 characters, while the prompt itself stays under 1,500. For a single take, leave enable_prompt_expansion off once the prompt is a precise shot description; switch it on when a one-line idea needs to be filled out.

Compare one change at a time

seed accepts 0 to 2147483647. Hold it while you change one thing, such as the camera move, the aspect ratio, or single against multi, and leave it out when you want variety. It steadies a comparison but does not promise a frame-identical rerun. Durations other than 5, 10 or 15 are rejected rather than rounded.

API quick start

Call the Wan 2.6 API in three steps

  1. Create an API key. Sign in to PopNow and create a key in the API console. Keys start with sk-popnow- and use the same credits as the website.
  2. Send the request. POST /jobs/createTask with model alibaba/wan-2.6/text-to-video and an input object that follows the parameter table. The response returns a task ID straight away.
  3. Get the result. Poll GET /jobs/recordInfo with the task ID, or pass a callBackUrl and we post the result to it. Download the output links when the task succeeds.
# 1. Create the task. Keep the Idempotency-Key if you retry after a network error.
export IDEMPOTENCY_KEY="$(uuidgen)"
curl -X POST https://api.popnow.ai/api/v1/jobs/createTask \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $IDEMPOTENCY_KEY" \
  -d '{
  "model": "alibaba/wan-2.6/text-to-video",
  "input": {
    "prompt": "A slow aerial shot drifting over a misty pine forest at sunrise",
    "aspect_ratio": "16:9",
    "resolution": "720p",
    "duration_seconds": 5,
    "shot_type": "single"
  }
}'

# 2. Copy data.taskId from the response, then poll until state is succeeded, failed, canceled or expired.
TASK_ID="TASK_ID_FROM_RESPONSE"
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=$TASK_ID" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

Replace the prompt and any links with your own. The API tab has the response, polling and callback reference.

Wan 2.6 API questions

How much does the Wan 2.6 API cost?

Wan 2.6 starts at 49 credits ($0.49) for a 5-second clip with Reference to Video, its cheapest task. Prices for Create Video by option: 720p 13.5 credits per second, 1080p 20.25 credits per second. Credits are the same as on the website (1 credit = $0.01), new accounts get 30 free credits, and failed tasks are refunded.

What is the model name for Wan 2.6 in the API?

Put alibaba/wan-2.6/text-to-video for Create Video; alibaba/wan-2.6/image-to-video for Image to Video; alibaba/wan-2.6/reference-to-video for Reference to Video in the model field of POST /jobs/createTask.

What does multi-shot do?

With shot_type set to multi, the model may cut between several shots inside one clip. Write the prompt as numbered shots so each cut has a purpose; use single when continuity matters more. Prompt expansion is switched on for multi requests, since the cuts are planned while the brief is expanded.

Can I send a reference clip or several images?

Yes, on reference-to-video: it takes up to three reference clips and up to two still images, five references at most, and recasts what they show into a scene you write. To animate a single still as the opening frame, use image-to-video.

Is there an aspect ratio parameter?

On text-to-video and reference-to-video, yes: 16:9, 9:16, 1:1, 4:3 or 3:4 at either resolution. Image-to-video keeps the proportions of the frame you send, so crop before that call.

What changed in Wan 2.6?

Multi-shot edits, 15-second clips at 720p and 1080p, and audio generated alongside the picture.

What are the limits of the Wan 2.6 API?

Clip length: 5–15 s; Resolutions: 720p · 1080p; Aspect ratios: 16:9 · 9:16 · 1:1 · 4:3 · 3:4; Prompt length (characters): 1,500. Requests outside these limits are rejected before anything is charged.

Can I try Wan 2.6 without writing code?

Yes. The Playground runs Wan 2.6 on your PopNow credits, needs no API key, and shows the matching code for every run.

All Wan models

Wan 2.6 Flash takes the same requests for less, with a little less fine detail. Wan 3.0 runs longer clips, up to 30 seconds.

More about Wan 2.6