Source: https://ailoot.ai/models/en/alibaba-wan-2-6/
Canonical: https://ailoot.ai/models/en/alibaba-wan-2-6/
Language: en

# Alibaba: Wan 2.6

[Markdown](https://ailoot.ai/models/en/alibaba-wan-2-6/index.md) · [JSON](https://ailoot.ai/models/en/alibaba-wan-2-6/facts.json)

## [Alibaba: Wan 2.6](https://ailoot.ai/models/en/alibaba-wan-2-6/)

Alibaba Wan 2.6 generates videos with synchronized sound from text, a starting image or visual references. Its maker modes support 720p or 1080p MP4, with 2–15 seconds for text/image generation and 2–10 seconds for references. Shot-type controls and character-indexed references distinguish its workflow.

- [**Ailoot Ultra · Video** `POST /v1/videos` `alibaba/wan-2.6`](https://ailoot.ai/models/en/alibaba-wan-2-6/#method-0)

About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

Alibaba Wan 2.6 is a video-generation family with distinct text-to-video, first-frame image-to-video and reference-to-video profiles. The maker documents synchronized audio and multi-shot narratives. A written scene can become a clip, a prepared still can establish the opening or visual references can guide characters and objects in a new scene. The useful output is the completed short video and its sound, prepared for review or use in an edited sequence.

For text generation, describe the subject, environment, movement, camera and sound. The legacy 2.6 text guide accepts Chinese or English prompts up to 1,500 characters, with a separate 500-character negative prompt; longer text is truncated. For a product animation, follow a toy delivery van crossing a workbench, pause beside a small parcel and end on the parcel as a quiet mechanical sound marks the stop. Keep the sequence simple enough that its central action remains easy to judge.

Multi-shot control is a specific part of the 2.6 workflow. The maker’s text guide offers single or multi shot\_type settings, with single as the default. In that text mode the setting takes effect with prompt rewriting enabled, and the parameter has priority over contradictory wording in the brief. Describe the shots and timing consistently with the selected setting. The later Wan 2.7 guide instead interprets shot structure directly from the prompt, so that newer preparation should not silently replace this edition’s documented controls.

First-frame generation uses an image to establish the opening and a prompt to describe what follows. Prepare the intended crop, subject and visual details in the still before asking for motion. The maker’s comparison identifies first/last-frame and source-clip continuation as additions in the 2.7 image workflow, rather than controls to assign to 2.6’s first-frame profile. For a product animation, review the object through the whole movement and inspect whether its shape, markings and scene remain suitable for the intended shot.

The current legacy 2.6 reference API accepts images and videos through an ordered reference list. It permits up to five images and three videos, with a combined maximum of five files. Each reference should contain one subject. The first maps to character1, the second to character2 and so on; use those identifiers in the prompt rather than borrowing Wan 2.7’s type-specific labels. Describe each character’s action and lines clearly so a multi-character interaction can be checked for attribution and identity.

The reference guide lists JPEG/JPG, PNG without transparency, BMP and WEBP images up to 20 MB, with each dimension between 240 and 8,000 pixels. Reference video may be MP4 or MOV up to 100 MB; the current reference\_urls field accepts one-to-thirty-second videos. The deprecated video-only field has a different minimum duration and is not the same preparation contract. Choose the source passage and subject that should inform the scene, and keep the reference roles explicit. A recognisable character can still be placed or voiced incorrectly in the result.

The maker’s text generation supports supplied audio through its documented audio source field, and the output modes include sound synchronized with the picture. State the intended dialogue, performance and atmosphere in the brief and review the actual words and effects. The reference API’s optional audio toggle is specifically labelled for the Flash reference variant; it is not a universal silent-video control to assume for every 2.6 mode. Sound and picture both need inspection against the intended scene.

Current maker specifications list 720p and 1080p output, with two-to-fifteen-second text and image generation and two-to-ten-second reference generation. Its video guides describe MP4 at 30 fps, while the reference API selects an explicit width-by-height size rather than a bare ratio label. Landscape, portrait and square options have their own documented dimensions. Keep the selected mode’s duration and size rules with the brief instead of borrowing Wan 3.0’s thirty-second generation allowance or a different edition’s adaptive configuration.

Generation is processed as a task, and a successful result supplies the video location. The maker documents twenty-four-hour result-link validity. Retain the actual clip, source references and prompt for the editing review. A fixed seed can help compare requests, but the legacy guide explicitly says it does not guarantee identical results. Review continuity, reference identity, object contact, requested shot structure, dialogue and visible details. The next correction should address the specific problem found while preserving the successful direction of the shot.

**Ailoot Ultra · Video** `POST /v1/videos` `alibaba/wan-2.6`

[`alibaba/wan-2.6`](https://ailoot.ai/models/en/#m=alibaba%2Fwan-2.6&route=Ultra&caller=alibaba%2Fwan-2.6&fmt=videos)

Alibaba /`alibaba/wan-2.6`

### Overview

Alibaba Wan 2.6 generates videos with synchronized sound from text, a starting image or visual references. Its maker modes support 720p or 1080p MP4, with 2–15 seconds for text/image generation and 2–10 seconds for references. Shot-type controls and character-indexed references distinguish its workflow.

Accepted inputs

Text · Images

Results

Video

### Available in Ailoot · inputs & methods

**Ailoot Ultra · Video** `POST /v1/videos`

Input types

`text`, `image`

Output types

`video`

Output format

original MP4 bytes; no normalization/transcode

| Field | Type | Requirement | Values & limits | Default |
| --- | --- | --- | --- | --- |
| Field`model` | Type`string` | RequirementRequired | Values & limits alibaba/wan-2.6 | Default— |
| Field`prompt` | Type`string` | RequirementRequired | Values & limits | Default— |
| Field`duration` | Type`integer` | RequirementRequired | Values & limits 5, 10 Minimum: 1 Maximum: 600 | Default— |
| Field`resolution` | Type`string` | RequirementOptional | Values & limits 720p, 1080p | Default— |
| Field`aspect_ratio` | Type`string` | RequirementOptional | Values & limits 16:9, 9:16 | Default— |
| Field`generate_audio` | Type`boolean` | RequirementOptional | Values & limits false, true | Default— |
| Field`frame_images` | Type`array` | RequirementOptional | Values & limits Minimum items: 1 Maximum items: 1 Input content: Array of frame objects. Each object has type=image\_url, image\_url containing url, and frame\_type. Use an HTTPS image URL and set frame\_type to first\_frame. Each frame role appears at most once. Exact keys: type, image\_url, frame\_type Conditions: These keys describe each frame object; image\_url contains only url. Omit frame\_images for a text-only request. | Default— |
| Field`input_references` | Type`array` | RequirementOptional | Values & limits | Default— |
| Field`size` | Type`string` | RequirementOptional | Values & limits 1280x720, 1080x1920, 720x1280, 1920x1080 Pattern: ^\[1-9\]\[0-9\]\*x\[1-9\]\[0-9\]\*$ | Default— |
| Field`seed` | Type`integer` | RequirementOptional | Values & limits Minimum: -9,223,372,036,854,775,808 Maximum: 9,223,372,036,854,775,807 | Default— |
| Field`callback_url` | Type`string` | RequirementOptional | Values & limits Pattern: ^https:// | Default— |
| Field`session_id` | Type`string` | RequirementOptional | Values & limits | Default— |
| Field`trace` | Type`object` | RequirementOptional | Values & limits | Default— |
| Field`user` | Type`string` | RequirementOptional | Values & limits | Default— |

Input material combinations

**Text to video** · A written prompt. · Required: model, prompt, duration

`Provide prompt as text and duration as whole seconds. Choose a supported resolution; add an aspect ratio or use a listed size.`

`model`: Type: string · alibaba/wan-2.6

`prompt`: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes

**Image to video** · A written prompt and a first-frame image. · Required: model, prompt, duration, frame\_images

`frame_images is an array. Each frame object has type, image_url and frame_type; image_url contains url. Set type to image_url. Use first_frame. Each frame role appears at most once. Supply a public HTTPS image URL for each frame. Choose a supported resolution; add an aspect ratio or use a listed size.`

Exact keys: type, image\_url, frame\_type

`model`: Type: string · alibaba/wan-2.6

`prompt`: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes

Method parameters and lifecycle

| Parameter | Contract |
| --- | --- |
| Parameter`content_type` | Contractapplication/json |
| Parameter`required` | Contractmodel, prompt, duration |
| Parameter`material_types` | Contracttext, image |
| Parameter`additional_properties` | Contractfalse |
| Parameter`optional_controls` | Contractresolution, aspect\_ratio, generate\_audio, frame\_images, input\_references, size, seed, callback\_url, session\_id, trace, user |

Lifecycle: `submit_once_poll_original`

`GET /v1/videos/{public_id}`

`GET /v1/videos/{public_id}/content`

### Pricing

##### How the final charge is calculated

The displayed rates estimate the cost before generation. The final charge is calculated from the cost recorded for the original generation. Measured output duration and forecast quantities are not the final billable quantity.

Tariff references do not add request options. Supported parameters are listed for the selected method.

Fast mode

Not specified When fast mode is selected

Flex mode

Not specified When flex mode is selected

Maximum reasoning effort

Not specified When maximum reasoning effort uses the default adjustment

#### Estimated rates for comparison

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Rate schedule | Forecast quantity | Charge component | Reference resolution | Reference mode | Billing unit | Billing conditions | Charge |
| --- | --- | --- | --- | --- | --- | --- | --- | --- |
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge component— | Reference resolution— | Reference mode— | Billing unit— | Billing conditions— | Charge Input · Input tokens · Estimate for comparison only **—** / 1K tokens Output · Output tokens · Estimate for comparison only **—** / 1K tokens Input · Cache read · Estimate for comparison only **—** / 1K tokens Input · Cache write · Estimate for comparison only **—** / 1K tokens Input · Cache write, 1 hour · Estimate for comparison only **—** / 1K tokens |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Reference resolution— | Reference mode— | Billing unitper video second | Billing conditionsgeneration mode: image\_to\_video; resolution: 1080p | Charge Output · Video price · Estimate for comparison only **$0.3** per video second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Reference resolution— | Reference mode— | Billing unitper video second | Billing conditionsgeneration mode: image\_to\_video; resolution: 720p | Charge Output · Video price · Estimate for comparison only **$0.2** per video second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Reference resolution— | Reference mode— | Billing unitper video second | Billing conditionsgeneration mode: text\_to\_video; resolution: 1080p | Charge Output · Video price · Estimate for comparison only **$0.24** per video second |
| ConfigurationText to video · 480p · reference rate | Rate schedule— | Forecast quantity— | Charge componentreference\_output\_rate | Reference resolution480p | Reference modeText to video | Billing unitper output second | Billing conditions— | Charge Output · Output video second reference rate · Estimate for comparison only **$0.08** per output second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Reference resolution— | Reference mode— | Billing unitper video second | Billing conditionsgeneration mode: text\_to\_video; resolution: 720p | Charge Output · Video price · Estimate for comparison only **$0.16** per video second |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge component— | Reference resolution— | Reference mode— | Billing unit— | Billing conditions— | Charge Output · Estimated generation cost · Estimate for comparison only **$0.8** estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |

Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. [How reservation and settlement work →](https://ailoot.ai/docs/en/billing/reserve/)

#### Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Video configuration price references

#### Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

| Configuration | Billing conditions | Charge |
| --- | --- | --- |
| ConfigurationVideo price | Billing conditionsgeneration mode: text\_to\_video; resolution: 480p | Charge Output · Video price **$0.08** per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsgeneration mode: text\_to\_video; resolution: 720p | Charge Output · Video price **$0.16** per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsgeneration mode: image\_to\_video; resolution: 720p | Charge Output · Video price **$0.2** per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsgeneration mode: text\_to\_video; resolution: 1080p | Charge Output · Video price **$0.24** per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsgeneration mode: image\_to\_video; resolution: 1080p | Charge Output · Video price **$0.3** per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |

### Example requests

#### Ailoot Ultra · Video

curl · create video

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_REQUEST'
from pathlib import Path
Path('request.json').write_text('{"aspect_ratio":"16:9","duration":5,"model":"alibaba/wan-2.6","prompt":"A serene mountain landscape at sunset","resolution":"720p"}', encoding='utf-8')
PY_REQUEST
curl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \
  -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \
  --data-binary @request.json -D response-headers.txt -o result.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path('result.json').read_text())
print(json.dumps(r,ensure_ascii=False,indent=2))
print('Keep the complete JSON and response headers; do not resubmit an unknown creation.')
PY_RESULT
```

### Receive and save results

#### Ailoot Ultra · Video

signed owned content URLs

- `GET /v1/videos/{public_id}`
- `GET /v1/videos/{public_id}/content`

##### Check job status

GET original status

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
python3 - <<'PY_STATUS_URL'
import json
from pathlib import Path
from urllib.parse import quote
r=json.loads(Path('result.json').read_text())
if not isinstance(r.get('id'),str) or not r['id']:raise SystemExit('Keep the original response and headers for reconciliation; no returned ID')
Path('status-url.txt').write_text('https://api.ailoot.ai/v1/videos/'+quote(r['id'],safe=''))
PY_STATUS_URL
curl --fail-with-body --silent --show-error "$(cat status-url.txt)" \
  -H "Authorization: Bearer $AILOOT_API_KEY" -D status-headers.txt -o status.json
python3 - <<'PY_RESULT'
import json
from pathlib import Path
r=json.loads(Path('status.json').read_text())
print(json.dumps(r,ensure_ascii=False,indent=2))
print('Keep the complete JSON and response headers; do not resubmit an unknown creation.')
PY_RESULT
```

Other content reads

Save every completed owned output

```bash
set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_ASSETS'
import json,os,subprocess
from pathlib import Path
from urllib.parse import urljoin,urlsplit
r=json.loads(Path('status.json').read_text())
if r.get('status')!='completed':raise SystemExit('Keep the original ID and read its status; never recreate an unknown job')
if not isinstance(r.get('data'),list) or not r['data']:raise SystemExit('Keep the complete original status; no completed outputs supplied')
urls=[]
for i,u in enumerate(r.get('data',[])):
    if not isinstance(u,str):raise SystemExit('Keep the original response; unexpected asset shape')
    urls.append((str(i),u))
for label,path in urls:
    u=urljoin('https://api.ailoot.ai',path);z=urlsplit(u)
    if z.scheme!='https' or z.netloc!='api.ailoot.ai' or z.username or z.password:raise SystemExit('Use the actual returned Ailoot owned content URL')
    target=Path('owned-'+label+'.bin')
    subprocess.run(['curl','--fail-with-body','--silent','--show-error',u,'-H','Authorization: Bearer '+os.environ['AILOOT_API_KEY'],'-D',str(target)+'.headers','-o',str(target)],check=True)
print('All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.')
PY_ASSETS
```

##### Keep all completed results

Save every completed video or returned file; retrieve every actual returned asset URL.

Keep every actual owned output and its returned measured metadata.

##### If the original response needs checking

503 result\_pending\_check + originalid + X-Should-Retry:false; never replay original

Response fields

| Field | Type | Meaning |
| --- | --- | --- |
| Field`index` | Typeinteger | MeaningZero-based position of this video in the outputs list. |
| Field`content_url` | Typestring | MeaningSigned HTTPS download URL for this completed video. |
| Field`sha256` | Typestring \| null | MeaningSHA-256 digest of the original video bytes; null if unavailable. |
| Field`size_bytes` | Typeinteger \| null | MeaningSize of the original video file in bytes; null if unavailable. |
| Field`duration_ms` | Typeinteger \| null | MeaningMeasured video duration in milliseconds; null if unavailable. |
| Field`width` | Typeinteger \| null | MeaningVideo width in pixels; null if unavailable. |
| Field`height` | Typeinteger \| null | MeaningVideo height in pixels; null if unavailable. |
| Field`video_codec` | Typestring \| null | MeaningVideo codec identifier; null if not recorded. |
| Field`has_audio` | Typeboolean \| null | MeaningWhether the video contains an audio track; null if not measured. |
| Field`audio_codec` | Typestring \| null | MeaningAudio codec identifier; null when no identifier is recorded. |

Errors and next steps

| Response | Condition | Next step |
| --- | --- | --- |
| Response404 · `not_found_error` | ConditionVideo access is unavailable, or this video ID was not found. | Next stepCheck video access. For an existing video, use its original public ID and the same API key. |
| Response401 · `authentication_error` | ConditionThe API key does not match the authenticated account. | Next stepCheck your API key and account access before submitting. |
| Response400 · `invalid_request_error` | ConditionThe request could not be read, or the download index is invalid. | Next stepCorrect the request body. For a download, choose an output index returned by the original task. |
| Response422 · `price_unavailable` | ConditionThe selected video configuration cannot be priced. | Next stepChoose a supported video configuration and complete its required options before submitting a corrected request. |
| Response422 · `invalid_request_error` | ConditionA video input or original continuation task is invalid. | Next stepUse valid HTTPS inputs. For continuation, use your completed original public video ID with the same API key. |
| Response402 · `billing_error` | ConditionThe available balance or limits do not allow a reservation. | Next stepCheck your available balance and limits before sending a new request. |
| Response503 · `server_error` | ConditionVideo verification, storage or service access is temporarily unavailable. | Next stepWait for service availability. If you already have a video ID, check that original task instead of creating another generation. |
| Response503 · `result_pending_check` | ConditionThe original video result and charge need checking. | Next stepKeep the returned video ID and check that task. Do not send a replacement generation request while it is being checked. |
| Response503 · `owned_result_unavailable` | ConditionThe existing video download is temporarily unavailable. | Next stepCheck the same video task later and download its existing output. A new generation creates a separate operation. |
| Response409 · `video_not_ready` | ConditionThe video content has not been published. | Next stepCheck the original task status. Download after it reports completed; if it reports failed, follow its charge-check notice. |

### Aliases

#### Model aliases

**Ailoot Ultra** [`alibaba/wan-2.6`](https://ailoot.ai/models/en/#m=alibaba%2Fwan-2.6&route=Ultra&caller=alibaba%2Fwan-2.6&fmt=videos)

#### Method path aliases

Use the method paths shown above.

#### Related caller IDs

[`alibaba/wan-2.6`](https://ailoot.ai/models/en/#m=alibaba%2Fwan-2.6&route=Ultra&caller=alibaba%2Fwan-2.6&fmt=videos)

FAQ · Alibaba: Wan 2.6

What inputs and results are available?

`POST /v1/videos` · `alibaba/wan-2.6`: `text`, `image` → `video`

Which fields does the request use?

`POST /v1/videos` · `alibaba/wan-2.6`: `model`, `prompt`, `duration`, `resolution`, `aspect_ratio`, `generate_audio`, `frame_images`, `input_references`, `size`, `seed`, `callback_url`, `session_id`, `trace`, `user`

What limits apply?

`POST /v1/videos` · `alibaba/wan-2.6`: `duration.minimum`: `1`; `duration.maximum`: `600`; `frame_images.max_items`: `1`; `frame_images.min_items`: `1`; `seed.minimum`: `-9223372036854775808`; `seed.maximum`: `9223372036854775807`

Connect Ailoot to Claude Code, OpenCode, Hermes or your own app.

## The company and its project portfolio

The company and its project portfolio: millions of customers; monthly sales in the billions.

## Buy tokens at a discount.

Subscription discounts for regular use. Promo codes offer up to 50% off token purchases.

Subscription

Choose a discounted plan for your regular requests.

Promo code: up to 50% off

Enter your code at checkout. The price updates to reflect the current promotion.

Spending in your history

The model, tokens and amount are recorded for each request.

[Choose a subscription](https://ailoot.ai/docs/en/billing/subscriptions/) · [View model prices](https://ailoot.ai/models/en/)

## Connect the API to a product you sell.

Use Ailoot in SaaS, apps and bots under its official service offer and licence agreement. Request a reseller licence for resale.

Commercial application

Add text, image, video and audio generation to paid features in your service.

Reseller licence

Send a description of your project and how you provide access. Request written terms for use and resale.

Documents on the website

The service offer, licence agreement and data processing policy are available before you connect.

[Request a reseller licence](mailto:support@ailoot.ai) · [Service offer and licence agreement](https://ailoot.ai/legal/offer?lang=en)

## Ailoot · The company and its project portfolio





Ailoot combines established operating experience, a large client base, stable service and ongoing KPI control.





The company and its project portfolio: millions of customers; monthly sales in the billions.





Ailoot brings that operating experience to API access for AI features in customer products, agents, applications and automations.