Alibaba Wan 2.7 is a video-generation family with named text-to-video, image-to-video and reference-guided profiles. The manufacturer documents audio-synchronized scenes and multi-shot narratives, while its image workflow adds first/last-frame generation and continuation of an initial video. The useful result is a short clip with its sound, such as a product transition, a compact story or a continuation that fits an existing shot. Select the mode from the source material and the control needed over the beginning or ending.
For text-to-video, describe the subject, setting, action, camera, style and sound. A storyboard can identify each shot and time range, while a single-shot brief should say that the action remains continuous. The Wan 2.7 prompt guide lets the model interpret shot structure from the written brief rather than using 2.6’s shot_type control. The current text API accepts Chinese or English prompts up to 5,000 characters, with a separate 500-character negative prompt; excess text is truncated. Keep essential action and constraints clear within that allowance.
First-frame image-to-video animates a supplied opening image. First/last-frame generation also defines the endpoint and the motion connecting it. The 2.7 image guide supports a driving audio source alongside those frame combinations. Prepare endpoints that share a scene and an intended subject, and describe the transition rather than asking the model to reinterpret both images as unrelated style references. The output approximates the first image’s proportions; the guide treats resolution as a pixel-count tier and rounds encoded dimensions appropriately.
Video continuation begins with a source clip and can also use a closing image. The requested duration is the total returned video, including the original segment. The guide’s example combines a two-second source with ten seconds of new content into a twelve-second result. Prepare the source’s final action and say what happens next, so the camera and subject continue in a coherent direction. Review the join for appearance, movement, light and sound rather than assessing only the newly generated ending.
The maker’s current separate reference profile uses images or video to guide characters, objects or a scene. Its guide allows up to five reference images and videos in total and uses type-specific labels such as Image 1 and Video 1. Describe the role of each material and the intended interaction. For a reference-guided scene, show a character from one reference carrying the object from another through a specified location. Reference framing differs from first-frame generation: the brief can establish a new composition instead of requiring the video to open on one supplied still.
For custom audio in text generation, the documented formats are WAV and MP3, with a two-to-thirty-second duration and a 15 MB maximum. The selected video duration determines the portion used: longer audio is clipped to that duration, while audio shorter than the video leaves the remainder silent. Prepare the exact audio passage that belongs to the shot and leave room for the intended visual action. Without a supplied audio file, the maker describes generating background music or effects suited to the scene; inspect the actual sound and any requested speech with the picture.
The current model matrix lists 720p or 1080p MP4 at 30 fps, with two-to-fifteen-second text and image output. The separate reference profile is limited to two to ten seconds. Text generation offers 16:9, 9:16, 1:1, 4:3 and 3:4 framing. Image-conditioned tasks use their own approximate source-proportion rules, so prepare the input crop for the intended destination. A duration or aspect rule from the reference profile should not be substituted for the frame or continuation workflow.
The documented maker flow is asynchronous: a task identifier tracks processing, and a successful result supplies the video location. Results are documented with twenty-four-hour link validity, so retain the actual clip and the creative materials for editing review. Prompt rewriting, watermark and seed options belong to the selected interface. The maker says a fixed seed can improve reproducibility but does not guarantee an identical result. Compare the returned artifact with the brief rather than assuming settings alone preserve every detail.
Compared with Wan 2.6, the 2.7 image guide specifically adds first/last-frame control and video continuation through multimodal media inputs. Wan 3.0 introduces a different all-in-one structure and longer generation allowance. This 2.7 profile keeps its task-specific controls and limits. Review the whole scene for subject continuity, frame anchors, reference identity, dialogue, motion and joins, and make the next correction specific to the actual issue found.
", "aboutText": "Alibaba Wan 2.7 is a video-generation family with named text-to-video, image-to-video and reference-guided profiles. The manufacturer documents audio-synchronized scenes and multi-shot narratives, while its image workflow adds first/last-frame generation and continuation of an initial video. The useful result is a short clip with its sound, such as a product transition, a compact story or a continuation that fits an existing shot. Select the mode from the source material and the control needed over the beginning or ending.\n\nFor text-to-video, describe the subject, setting, action, camera, style and sound. A storyboard can identify each shot and time range, while a single-shot brief should say that the action remains continuous. The Wan 2.7 prompt guide lets the model interpret shot structure from the written brief rather than using 2.6’s shot_type control. The current text API accepts Chinese or English prompts up to 5,000 characters, with a separate 500-character negative prompt; excess text is truncated. Keep essential action and constraints clear within that allowance.\n\nFirst-frame image-to-video animates a supplied opening image. First/last-frame generation also defines the endpoint and the motion connecting it. The 2.7 image guide supports a driving audio source alongside those frame combinations. Prepare endpoints that share a scene and an intended subject, and describe the transition rather than asking the model to reinterpret both images as unrelated style references. The output approximates the first image’s proportions; the guide treats resolution as a pixel-count tier and rounds encoded dimensions appropriately.\n\nVideo continuation begins with a source clip and can also use a closing image. The requested duration is the total returned video, including the original segment. The guide’s example combines a two-second source with ten seconds of new content into a twelve-second result. Prepare the source’s final action and say what happens next, so the camera and subject continue in a coherent direction. Review the join for appearance, movement, light and sound rather than assessing only the newly generated ending.\n\nThe maker’s current separate reference profile uses images or video to guide characters, objects or a scene. Its guide allows up to five reference images and videos in total and uses type-specific labels such as Image 1 and Video 1. Describe the role of each material and the intended interaction. For a reference-guided scene, show a character from one reference carrying the object from another through a specified location. Reference framing differs from first-frame generation: the brief can establish a new composition instead of requiring the video to open on one supplied still.\n\nFor custom audio in text generation, the documented formats are WAV and MP3, with a two-to-thirty-second duration and a 15 MB maximum. The selected video duration determines the portion used: longer audio is clipped to that duration, while audio shorter than the video leaves the remainder silent. Prepare the exact audio passage that belongs to the shot and leave room for the intended visual action. Without a supplied audio file, the maker describes generating background music or effects suited to the scene; inspect the actual sound and any requested speech with the picture.\n\nThe current model matrix lists 720p or 1080p MP4 at 30 fps, with two-to-fifteen-second text and image output. The separate reference profile is limited to two to ten seconds. Text generation offers 16:9, 9:16, 1:1, 4:3 and 3:4 framing. Image-conditioned tasks use their own approximate source-proportion rules, so prepare the input crop for the intended destination. A duration or aspect rule from the reference profile should not be substituted for the frame or continuation workflow.\n\nThe documented maker flow is asynchronous: a task identifier tracks processing, and a successful result supplies the video location. Results are documented with twenty-four-hour link validity, so retain the actual clip and the creative materials for editing review. Prompt rewriting, watermark and seed options belong to the selected interface. The maker says a fixed seed can improve reproducibility but does not guarantee an identical result. Compare the returned artifact with the brief rather than assuming settings alone preserve every detail.\n\nCompared with Wan 2.6, the 2.7 image guide specifically adds first/last-frame control and video continuation through multimodal media inputs. Wan 3.0 introduces a different all-in-one structure and longer generation allowance. This 2.7 profile keeps its task-specific controls and limits. Review the whole scene for subject continuity, frame anchors, reference identity, dialogue, motion and joins, and make the next correction specific to the actual issue found.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "1d9a701306da1912c06bb497c2a23d1958942c73d262f10243b5adef018de96f", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "alibaba/wan-2.7Alibaba Wan 2.7 creates videos with sound from text, opening and closing images, or visual references. Its image workflow also continues a source clip, using the requested total duration. The maker lists 720p or 1080p MP4 at 30 fps: 2–15 seconds for text/image modes and up to 10 seconds for reference generation.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Alibaba Wan 2.7 is a video-generation family with named text-to-video, image-to-video and reference-guided profiles. The manufacturer documents audio-synchronized scenes and multi-shot narratives, while its image workflow adds first/last-frame generation and continuation of an initial video. The useful result is a short clip with its sound, such as a product transition, a compact story or a continuation that fits an existing shot. Select the mode from the source material and the control needed over the beginning or ending.
For text-to-video, describe the subject, setting, action, camera, style and sound. A storyboard can identify each shot and time range, while a single-shot brief should say that the action remains continuous. The Wan 2.7 prompt guide lets the model interpret shot structure from the written brief rather than using 2.6’s shot_type control. The current text API accepts Chinese or English prompts up to 5,000 characters, with a separate 500-character negative prompt; excess text is truncated. Keep essential action and constraints clear within that allowance.
First-frame image-to-video animates a supplied opening image. First/last-frame generation also defines the endpoint and the motion connecting it. The 2.7 image guide supports a driving audio source alongside those frame combinations. Prepare endpoints that share a scene and an intended subject, and describe the transition rather than asking the model to reinterpret both images as unrelated style references. The output approximates the first image’s proportions; the guide treats resolution as a pixel-count tier and rounds encoded dimensions appropriately.
Video continuation begins with a source clip and can also use a closing image. The requested duration is the total returned video, including the original segment. The guide’s example combines a two-second source with ten seconds of new content into a twelve-second result. Prepare the source’s final action and say what happens next, so the camera and subject continue in a coherent direction. Review the join for appearance, movement, light and sound rather than assessing only the newly generated ending.
The maker’s current separate reference profile uses images or video to guide characters, objects or a scene. Its guide allows up to five reference images and videos in total and uses type-specific labels such as Image 1 and Video 1. Describe the role of each material and the intended interaction. For a reference-guided scene, show a character from one reference carrying the object from another through a specified location. Reference framing differs from first-frame generation: the brief can establish a new composition instead of requiring the video to open on one supplied still.
For custom audio in text generation, the documented formats are WAV and MP3, with a two-to-thirty-second duration and a 15 MB maximum. The selected video duration determines the portion used: longer audio is clipped to that duration, while audio shorter than the video leaves the remainder silent. Prepare the exact audio passage that belongs to the shot and leave room for the intended visual action. Without a supplied audio file, the maker describes generating background music or effects suited to the scene; inspect the actual sound and any requested speech with the picture.
The current model matrix lists 720p or 1080p MP4 at 30 fps, with two-to-fifteen-second text and image output. The separate reference profile is limited to two to ten seconds. Text generation offers 16:9, 9:16, 1:1, 4:3 and 3:4 framing. Image-conditioned tasks use their own approximate source-proportion rules, so prepare the input crop for the intended destination. A duration or aspect rule from the reference profile should not be substituted for the frame or continuation workflow.
The documented maker flow is asynchronous: a task identifier tracks processing, and a successful result supplies the video location. Results are documented with twenty-four-hour link validity, so retain the actual clip and the creative materials for editing review. Prompt rewriting, watermark and seed options belong to the selected interface. The maker says a fixed seed can improve reproducibility but does not guarantee an identical result. Compare the returned artifact with the brief rather than assuming settings alone preserve every detail.
Compared with Wan 2.6, the 2.7 image guide specifically adds first/last-frame control and video continuation through multimodal media inputs. Wan 3.0 introduces a different all-in-one structure and longer generation allowance. This 2.7 profile keeps its task-specific controls and limits. Review the whole scene for subject continuity, frame anchors, reference identity, dialogue, motion and joins, and make the next correction specific to the actual issue found.
POST /v1/videostextvideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits alibaba/wan-2.7 | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Maximum UTF-8 bytes: 10,000 Non-whitespace required: Yes | Default— |
Fieldduration | Typeinteger | RequirementRequired | Values & limits 2, 3, 4, 5, 6, 7, 8, 9, 10 | Default— |
Fieldresolution | Typestring | RequirementRequired | Values & limits 720p | Default— |
Fieldaspect_ratio | Typestring | RequirementRequired | Values & limits 16:9, 9:16, 1:1, 4:3, 3:4 | Default— |
Fieldgenerate_audio | Typeboolean | RequirementRequired | Values & limits false, true | Default— |
Text to video · Required: prompt
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt, duration, resolution, aspect_ratio, generate_audio |
Parameteradditional_properties | Contractfalse |
Parameterparameters | Contract{"name":"model","type":"string","required":true,"enum":["alibaba/wan-2.7"]}, {"name":"prompt","type":"string","required":true,"non_whitespace":true,"max_utf8_bytes":10000}, {"name":"duration","type":"integer","required":true,"enum":[2,3,4,5,6,7,8,9,10]}, {"name":"resolution","type":"string","required":true,"enum":["720p"]}, {"name":"aspect_ratio","type":"string","required":true,"enum":["16:9","9:16","1:1","4:3","3:4"]}, {"name":"generate_audio","type":"boolean","required":true,"enum":[false,true]} |
Parametermaterial_types | Contracttext |
Method aliases: /v1/videos/generations, /videos, /videos/generations
Lifecycle: submit_once_poll_original
GET /v1/videos/{request_id}
GET /v1/videos/generations/{request_id}
GET /v1/videos/{request_id}/content
GET /v1/videos/generations/{request_id}/content
Keep the complete response and the original returned IDs.
Never resubmit an unknown creation.
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.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Rate schedule | Forecast quantity | Audio generation choices | Resolution | Billing unit | Charge |
|---|---|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Audio generation choices— | Resolution— | Billing unit— | 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 |
| ConfigurationUltra | Rate schedule— | Forecast quantityRequested configuration; estimate only. | Audio generation choicesWithout audio · With audio | Resolution720p | Billing unitper output video second | Charge Output · estimated video second · Estimate for comparison only $0.2 per output video second The displayed rate estimates the cost before generation. The final charge is calculated from the cost recorded for the original generation. Physical video duration is not the billable quantity. |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Audio generation choices— | Resolution— | Billing unit— | Charge Output · Estimated generation cost · Estimate for comparison only $0.4 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationVideo price | Billing conditionsNo additional condition is declared in this pricing key. | Charge Output · Video price $0.2 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nimport json,os\nfrom pathlib import Path\np=json.loads('{"model": "alibaba/wan-2.7", "prompt": "a calm greenhouse", "duration": 6, "resolution": "720p", "aspect_ratio": "16:9", "generate_audio": true}')\nPath('request.json').write_text(json.dumps(p,ensure_ascii=False))\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('result.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\nmp4
GET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/videos/generations/{request_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_STATUS_URL'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nr=json.loads(Path('result.json').read_text())\nif not isinstance(r.get('id'),str) or not r['id']:raise SystemExit('Keep the original response and headers for reconciliation; no returned ID')\nPath('status-url.txt').write_text('https://api.ailoot.ai/v1/videos/'+quote(r['id'],safe=''))\nPY_STATUS_URL\ncurl --fail-with-body --silent --show-error "$(cat status-url.txt)" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -D status-headers.txt -o status.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('status.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_ASSETS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path('status.json').read_text())\nif r.get('status')!='completed':raise SystemExit('Keep the original ID and read its status; never recreate an unknown job')\nif not isinstance(r.get('data'),list) or not r['data']:raise SystemExit('Keep the complete original status; no completed outputs supplied')\nurls=[]\nfor i,u in enumerate(r.get('data',[])):\n if not isinstance(u,str):raise SystemExit('Keep the original response; unexpected asset shape')\n urls.append((str(i),u))\nfor label,path in urls:\n u=urljoin('https://api.ailoot.ai',path);z=urlsplit(u)\n 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')\n target=Path('owned-'+label+'.bin')\n 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)\nprint('All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.')\nPY_ASSETS\nSave every completed video or returned file; retrieve every actual returned asset URL.
Keep every completed data[] signed owned URL and the full status metadata. Save every output, including its generated audio. A valid AAC audio track can be present even with generate_audio=false; keep the complete original MP4 including that audio.
Read existing original job; never resubmit unknown send.
Maximum outputs: 4.
| Field | Type | Meaning |
|---|---|---|
Fieldid | Typestring | Meaning— |
Fieldobject | Typestring | Meaning— |
Fieldmodel | Typestring | Meaning— |
Fieldstatus | Typestring | Meaning— |
Fielddata[] | Typesigned content URL | Meaning— |
Fieldcharge_pending_check | Typeboolean | Meaning— |
Fielderror.code | Typestring | Meaning— |
Fielderror.message | Typestring | Meaning— |
Fieldoperation_id | Typestring | MeaningHTTP503 result_pending_check original status/content response: same original public video ID as id. |
Fielderror.type | Typestring | Meaningserver_error on HTTP503 result_pending_check. |
| Response | Condition | Next step |
|---|---|---|
Response400 · invalid_request_error | ConditionReading the raw request body fails before parsing the video profile | Next stepPreserve the returned response and correct the unreadable request body. |
Response422 · price_unavailable | ConditionParsing the exact video profile fails, or the complete parsed profile has no ready exact price card | Next stepPreserve the response; use the complete exact admitted profile and its published card. This branch runs before a provider send. |
Response409 · video_not_ready | ConditionOriginal result content is not yet available | Next stepPoll the original returned ID and respect Retry-After. |
Responseserver_error | ConditionThe returned response says the operation or result requires a check | Next stepKeep the original returned operation/task ID, request headers and response; continue supported reads of that original operation. Do not resubmit the creation request. |
Response503 · result_pending_check | ConditionGET original status/content: task is not published, original job is not failed/cancelled/expired, and local state is unknown or original job status is completed. | Next stepKeep original id and operation_id (same public video ID), response and headers; read only the original status/content. Never submit a new generation request. |
Ailoot Ultra alibaba/wan-2.7
/v1/videos/generations, /videos, /videos/generations