PixVerse v4.5 is a video-generation model with text-to-video and image-to-video capability. It takes a written scene brief and can use a supplied image as the visual starting point. Define a clear event, then judge the finished clip by how well its action, composition and timing serve that event.
A text-led brief should name the subject, location and visible movement. Include the physical details that distinguish the scene, such as the shape of an object or the lighting of a room. Describe the opening and the intended final view so the action has a direction that can be assessed.
An image-led brief starts from a prepared reference. Choose a view that shows the important face, object outline or material features clearly. Explain which elements move and how the camera relates to them. Save the original image with the generated sequence so appearance can be compared directly.
The documented catalogue includes landscape, portrait and square frame shapes, multiple resolution choices and normal or fast motion modes. Select the controls available in the chosen workflow and retain their values. Use the destination format to decide where the main action should remain within the frame.
For a scene intended for a short edit, identify the decisive beat. It may be a subject turning, an object reaching its destination or a camera revealing a detail. Build the shot around that moment and inspect whether the finished motion leads to it clearly. Select an ending that connects to the next part of the edit.
For atmosphere or environment studies, describe visible changes in light, weather or nearby materials. A reflection moving across a surface and leaves shifting in a breeze each offer a concrete visual event. Keep the main subject’s appearance consistent with the setting described in the brief.
Review continuity through the full sequence. Check the subject’s proportions, distinguishing details and relationship to nearby objects. Watch changes in overlap, surface appearance and camera position. Compare candidates at the intended viewing size and normal playback speed before choosing a shot.
Keep the prompt, reference image, selected settings and completed video together. When correcting a candidate, name the observed problem and revise the instruction connected to it. Preserve the useful action, setting and visual treatment so the next comparison answers a specific question about the scene.
", "aboutText": "PixVerse v4.5 is a video-generation model with text-to-video and image-to-video capability. It takes a written scene brief and can use a supplied image as the visual starting point. Define a clear event, then judge the finished clip by how well its action, composition and timing serve that event.\n\nA text-led brief should name the subject, location and visible movement. Include the physical details that distinguish the scene, such as the shape of an object or the lighting of a room. Describe the opening and the intended final view so the action has a direction that can be assessed.\n\nAn image-led brief starts from a prepared reference. Choose a view that shows the important face, object outline or material features clearly. Explain which elements move and how the camera relates to them. Save the original image with the generated sequence so appearance can be compared directly.\n\nThe documented catalogue includes landscape, portrait and square frame shapes, multiple resolution choices and normal or fast motion modes. Select the controls available in the chosen workflow and retain their values. Use the destination format to decide where the main action should remain within the frame.\n\nFor a scene intended for a short edit, identify the decisive beat. It may be a subject turning, an object reaching its destination or a camera revealing a detail. Build the shot around that moment and inspect whether the finished motion leads to it clearly. Select an ending that connects to the next part of the edit.\n\nFor atmosphere or environment studies, describe visible changes in light, weather or nearby materials. A reflection moving across a surface and leaves shifting in a breeze each offer a concrete visual event. Keep the main subject’s appearance consistent with the setting described in the brief.\n\nReview continuity through the full sequence. Check the subject’s proportions, distinguishing details and relationship to nearby objects. Watch changes in overlap, surface appearance and camera position. Compare candidates at the intended viewing size and normal playback speed before choosing a shot.\n\nKeep the prompt, reference image, selected settings and completed video together. When correcting a candidate, name the observed problem and revise the instruction connected to it. Preserve the useful action, setting and visual treatment so the next comparison answers a specific question about the scene.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "270d2c834d46cc2585e061d4838e6c81ffcfdf3d5b7a8e34f4d73e936178e439", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "pixverse-v4.5PixVerse v4.5 generates video from text or a supplied image. Plan the subject, movement and final frame, then use the documented framing, resolution and motion controls to develop a focused short scene.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
PixVerse v4.5 is a video-generation model with text-to-video and image-to-video capability. It takes a written scene brief and can use a supplied image as the visual starting point. Define a clear event, then judge the finished clip by how well its action, composition and timing serve that event.
A text-led brief should name the subject, location and visible movement. Include the physical details that distinguish the scene, such as the shape of an object or the lighting of a room. Describe the opening and the intended final view so the action has a direction that can be assessed.
An image-led brief starts from a prepared reference. Choose a view that shows the important face, object outline or material features clearly. Explain which elements move and how the camera relates to them. Save the original image with the generated sequence so appearance can be compared directly.
The documented catalogue includes landscape, portrait and square frame shapes, multiple resolution choices and normal or fast motion modes. Select the controls available in the chosen workflow and retain their values. Use the destination format to decide where the main action should remain within the frame.
For a scene intended for a short edit, identify the decisive beat. It may be a subject turning, an object reaching its destination or a camera revealing a detail. Build the shot around that moment and inspect whether the finished motion leads to it clearly. Select an ending that connects to the next part of the edit.
For atmosphere or environment studies, describe visible changes in light, weather or nearby materials. A reflection moving across a surface and leaves shifting in a breeze each offer a concrete visual event. Keep the main subject’s appearance consistent with the setting described in the brief.
Review continuity through the full sequence. Check the subject’s proportions, distinguishing details and relationship to nearby objects. Watch changes in overlap, surface appearance and camera position. Compare candidates at the intended viewing size and normal playback speed before choosing a shot.
Keep the prompt, reference image, selected settings and completed video together. When correcting a candidate, name the observed problem and revise the instruction connected to it. Preserve the useful action, setting and visual treatment so the next comparison answers a specific question about the scene.
POST /v1/videostext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits pixverse-v4.5 Conditions: Use this exact Ailoot routing selector. | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Conditions: Describe the scene and its motion. | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 16:9, 4:3, 1:1, 3:4, 9:16 Conditions: Use a listed selected-model aspect ratio. | Default— |
Fieldquality | Typestring | RequirementOptional | Values & limits 360p, 540p, 720p, 1080p Conditions: Use the listed selected-model quality value. | Default— |
Fieldmotion_mode | Typestring | RequirementOptional | Values & limits normal, fast Conditions: Use the listed selected-model motion mode. | Default— |
Fieldduration | Typeinteger | RequirementOptional | Values & limits 5, 8 Conditions: Use a listed duration; no unstated default. | Default— |
Fieldend_image | Typestring | RequirementOptional | Values & limits Conditions: An optional end frame selects a supported image mode. | Default— |
Fieldlip_sync_tts_content | Typestring | RequirementOptional | Values & limits Conditions: Optional selected-model speech content. | Default— |
Fieldlip_sync_tts_speaker_id | Typestring | RequirementOptional | Values & limits Conditions: Use an actual provider-supported voice ID; no voice ID is invented. | Default— |
Fieldimage | Typestring or array<string> | RequirementOptional | Values & limits Conditions: Use your actual publicly reachable image URL or base64 image; the selected model supports image input. | Default— |
Fieldnegative_prompt | Typestring | RequirementOptional | Values & limits Conditions: Describe content to avoid. | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parameteroptional | Contractaspect_ratio, quality, motion_mode, duration, end_image, lip_sync_tts_content, lip_sync_tts_speaker_id, image, negative_prompt |
Parametermaterial_types | Contracttext, image |
Parameterconditions | ContractUse this exact Ailoot routing selector., Describe the scene and its motion., Use a listed selected-model aspect ratio., Use the listed selected-model quality value., Use the listed selected-model motion mode., Use a listed duration; no unstated default., An optional end frame selects a supported image mode., Optional selected-model speech content., Use an actual provider-supported voice ID; no voice ID is invented., Use your actual publicly reachable image URL or base64 image; the selected model supports image input., Describe content to avoid. |
Method aliases: /v1/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/media/assets
GET /v1/media/assets/{asset_id}
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 | Charge |
|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | 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 |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge Output · Estimated generation cost · Estimate for comparison only $0.2 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncat > request.json <<'JSON'\n{\n "model": "pixverse-v4.5",\n "prompt": "A cat is walking on grass."\n}\nJSON\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\n# Create once; retain id, polling_url, original task identifiers and every header.\nset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\nexport AILOOT_API_KEY\npython3 - <<'PY_STATUS'\nimport json,os,subprocess\nfrom pathlib import Path\nfrom urllib.parse import urljoin,urlsplit\nr=json.loads(Path("result.json").read_text())\nu=urljoin("https://api.ailoot.ai",r["polling_url"])\np=urlsplit(u)\nif p.scheme!="https" or p.netloc!="api.ailoot.ai" or p.username or p.password:\n raise SystemExit("Unexpected returned polling URL; preserve the response")\nsubprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-D","status-headers.txt","-o","status.json"],check=True)\n# Read this same original polling_url again while pending.\n# Preserve unknown/result_pending_check; do not repeat creation.\nPY_STATUS\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())\nroles={}\ndef visit(v,path=""):\n if isinstance(v,dict):\n for k,x in v.items(): visit(x,path+"/"+k)\n elif isinstance(v,list):\n for i,x in enumerate(v): visit(x,path+"/"+str(i))\n elif isinstance(v,str):\n u=urljoin("https://api.ailoot.ai",v); p=urlsplit(u)\n if p.scheme=="https" and p.netloc=="api.ailoot.ai" and not p.username and not p.password and p.path.startswith("/v1/media/assets/") and p.path.endswith("/content"):\n roles.setdefault(u,[]).append(path)\nvisit(r)\nif not roles: raise SystemExit("No completed owned assets; retain the original status")\nmanifest=[]\nfor i,(u,paths) in enumerate(roles.items()):\n target=Path(f"asset-{i}.bin")\n subprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-o",str(target)],check=True)\n raw=target.read_bytes()\n if not raw: raise SystemExit("Empty asset; retain original status and metadata")\n ext="glb" if raw[:4]==b"glTF" else "png" if raw[:8]==b"\\x89PNG\\r\\n\\x1a\\n" else "jpg" if raw[:3]==b"\\xff\\xd8\\xff" else "webp" if raw[:4]==b"RIFF" and raw[8:12]==b"WEBP" else "mp4" if raw[4:8]==b"ftyp" else "bin"\n name=f"asset-{i}.{ext}"\n if target.name!=name: target.rename(name)\n manifest.append({"file":name,"response_paths":paths,"bytes":len(raw)})\nPath("asset-manifest.json").write_text(json.dumps(manifest,indent=2))\nprint("Saved",len(manifest),"unique owned assets; every response role retained")\nPY_ASSETS\nGET /v1/videos/{request_id}GET /v1/videos/generations/{request_id}GET /v1/videos/{request_id}/contentGET /v1/media/assetsGET /v1/media/assets/{asset_id}Save every completed video or returned file; retrieve every actual returned asset URL.
Retain the complete response and headers, original identifiers, every actual output and all usage/accounting fields. Save each unique owned asset and retain every role pointing to it.
Keep the returned public task or operation id and all headers. Read only the original task; unknown or result_pending_check does not authorize another creation.
| Field | Type |
|---|---|
Fieldid | Typestring |
Fieldpolling_url | Typestring |
Fieldprovider_task_id | Typestring |
Fieldtask_id | Typestring |
Fieldstatus | Typestring |
Fieldvideo_url | Typestring |
Ailoot Ultra pixverse-v4.5
/v1/videos/generations