CogVideoX 2 is Zhipu AI’s video-generation model for a written scene description or a supplied image. Text establishes the subject, setting and action; an image can provide the visual basis for the generated sequence. Use the input that best represents the material already available for the shot, then describe the visible motion the finished video should contain.
For text-driven creation, define one coherent event. A person opening a workshop door, a small boat moving past a pier or an object turning under steady light each gives the shot a readable purpose. State the important subject features, the viewpoint and the direction of movement. Choose an ending that can be used in the intended edit rather than leaving the scene’s final composition unspecified.
For image-based creation, prepare a clear view of the subject and describe how the scene should move from it. The maker accepts PNG, JPEG and JPG references up to 5 MB, supplied by image URL or encoded image data. Keep important edges, facial features and object details visible in the reference, and leave space for the requested action within the composition.
The maker limits the written prompt to 512 characters. Use this space for the decisive details: subject, action, setting and viewpoint. A short description that explains which object moves and what remains fixed is easier to assess than a list of broad style adjectives. If the result misses the goal, revise the instruction tied to the observed motion or framing problem.
The published output sizes include square, landscape and portrait formats, with choices ranging from 720×480 through 3840×2160 pixels. The maker also documents 30 or 60 frames per second. Select the shape and frame rate for the destination before generation, then inspect the actual clip to see whether the subject and its important details remain readable in that framing.
Quality and speed are named output modes in the maker’s workflow. Optional AI-generated sound effects are controlled separately from the visual brief. Retain the selected mode and sound-effect setting with the prompt and any reference image so different candidate clips can be compared using their actual generation settings.
Generation is asynchronous: a task identity is returned before the finished video is available. Keep that identity through result checking and preserve all completed video files associated with the operation. Save the clip itself for editing, together with the source image when used, rather than depending on a temporary result location or a preview frame.
Review the entire sequence for continuity, timing and the requested action. A product shot needs stable shape and material details through movement; a character shot needs coherent appearance and gestures. Check the final composition and any generated sound against the shot’s purpose. Keep the successful scene elements when revising a concrete mismatch, and use the same viewing conditions to compare the original and revised videos.
", "aboutText": "CogVideoX 2 is Zhipu AI’s video-generation model for a written scene description or a supplied image. Text establishes the subject, setting and action; an image can provide the visual basis for the generated sequence. Use the input that best represents the material already available for the shot, then describe the visible motion the finished video should contain.\n\nFor text-driven creation, define one coherent event. A person opening a workshop door, a small boat moving past a pier or an object turning under steady light each gives the shot a readable purpose. State the important subject features, the viewpoint and the direction of movement. Choose an ending that can be used in the intended edit rather than leaving the scene’s final composition unspecified.\n\nFor image-based creation, prepare a clear view of the subject and describe how the scene should move from it. The maker accepts PNG, JPEG and JPG references up to 5 MB, supplied by image URL or encoded image data. Keep important edges, facial features and object details visible in the reference, and leave space for the requested action within the composition.\n\nThe maker limits the written prompt to 512 characters. Use this space for the decisive details: subject, action, setting and viewpoint. A short description that explains which object moves and what remains fixed is easier to assess than a list of broad style adjectives. If the result misses the goal, revise the instruction tied to the observed motion or framing problem.\n\nThe published output sizes include square, landscape and portrait formats, with choices ranging from 720×480 through 3840×2160 pixels. The maker also documents 30 or 60 frames per second. Select the shape and frame rate for the destination before generation, then inspect the actual clip to see whether the subject and its important details remain readable in that framing.\n\nQuality and speed are named output modes in the maker’s workflow. Optional AI-generated sound effects are controlled separately from the visual brief. Retain the selected mode and sound-effect setting with the prompt and any reference image so different candidate clips can be compared using their actual generation settings.\n\nGeneration is asynchronous: a task identity is returned before the finished video is available. Keep that identity through result checking and preserve all completed video files associated with the operation. Save the clip itself for editing, together with the source image when used, rather than depending on a temporary result location or a preview frame.\n\nReview the entire sequence for continuity, timing and the requested action. A product shot needs stable shape and material details through movement; a character shot needs coherent appearance and gestures. Check the final composition and any generated sound against the shot’s purpose. Keep the successful scene elements when revising a concrete mismatch, and use the same viewing conditions to compare the original and revised videos.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "432fc8210e84eafb57f6dd79f7c30acfcfe0eff4a7beb6c977cb58b2d2a66cd4", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "cogvideox-2CogVideoX 2 generates video from a text description or a supplied image. The maker documents selectable frame sizes, 30 or 60 fps, quality or speed modes and optional generated sound effects for shaping a short visual scene.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
CogVideoX 2 is Zhipu AI’s video-generation model for a written scene description or a supplied image. Text establishes the subject, setting and action; an image can provide the visual basis for the generated sequence. Use the input that best represents the material already available for the shot, then describe the visible motion the finished video should contain.
For text-driven creation, define one coherent event. A person opening a workshop door, a small boat moving past a pier or an object turning under steady light each gives the shot a readable purpose. State the important subject features, the viewpoint and the direction of movement. Choose an ending that can be used in the intended edit rather than leaving the scene’s final composition unspecified.
For image-based creation, prepare a clear view of the subject and describe how the scene should move from it. The maker accepts PNG, JPEG and JPG references up to 5 MB, supplied by image URL or encoded image data. Keep important edges, facial features and object details visible in the reference, and leave space for the requested action within the composition.
The maker limits the written prompt to 512 characters. Use this space for the decisive details: subject, action, setting and viewpoint. A short description that explains which object moves and what remains fixed is easier to assess than a list of broad style adjectives. If the result misses the goal, revise the instruction tied to the observed motion or framing problem.
The published output sizes include square, landscape and portrait formats, with choices ranging from 720×480 through 3840×2160 pixels. The maker also documents 30 or 60 frames per second. Select the shape and frame rate for the destination before generation, then inspect the actual clip to see whether the subject and its important details remain readable in that framing.
Quality and speed are named output modes in the maker’s workflow. Optional AI-generated sound effects are controlled separately from the visual brief. Retain the selected mode and sound-effect setting with the prompt and any reference image so different candidate clips can be compared using their actual generation settings.
Generation is asynchronous: a task identity is returned before the finished video is available. Keep that identity through result checking and preserve all completed video files associated with the operation. Save the clip itself for editing, together with the source image when used, rather than depending on a temporary result location or a preview frame.
Review the entire sequence for continuity, timing and the requested action. A product shot needs stable shape and material details through movement; a character shot needs coherent appearance and gestures. Check the final composition and any generated sound against the shot’s purpose. Keep the successful scene elements when revising a concrete mismatch, and use the same viewing conditions to compare the original and revised videos.
POST /v1/videostextvideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits cogvideox-2 Conditions: Use the exact Ailoot model selector. | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Conditions: Describe the scene and motion. | Default— |
Fieldquality | Typeboolean | RequirementOptional | Values & limits Conditions: Optional quality flag; this selected schema supplies no compatible enum or default. | Default— |
Fieldwith_audio | Typeboolean | RequirementOptional | Values & limits Conditions: Generate AI sound effects when enabled. | Defaultfalse |
Fieldsize | Typestring | RequirementOptional | Values & limits Conditions: Supply the documented size string when selecting explicit dimensions. | Default— |
Fieldfps | Typestring | RequirementOptional | Values & limits 30, 60 Conditions: Frame rate is represented as a string on this selected native method. | Default30 |
Fieldduration | Typestring | RequirementOptional | Values & limits 5, 10 Conditions: Duration in seconds is represented as a string on this selected native method. | Default5 |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parameteroptional | Contractquality, with_audio, size, fps, duration |
Parametermaterial_types | Contracttext |
Parameterconditions | ContractUse the exact Ailoot model selector., Describe the scene and motion., Optional quality flag; this selected schema supplies no compatible enum or default., Generate AI sound effects when enabled., Supply the documented size string when selecting explicit dimensions., Frame rate is represented as a string on this selected native method., Duration in seconds is represented as a string on this selected native method. |
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 | Billing quantity | Charge |
|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Billing 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 |
| ConfigurationPer request | Rate schedule— | Forecast quantity— | Billing quantityone request | Charge Input · Estimate for comparison only $0.2 per request |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing quantity— | 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": "cogvideox-2",\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 |
Fieldid | Typestring |
Fieldtask_status | Typestring |
Fieldvideo_result[].url | Typestring |
Ailoot Ultra cogvideox-2
/v1/videos/generations