Mochi 1 is Genmo’s text-to-video model for turning a written scene description into moving imagery. The maker emphasizes motion and prompt adherence, with a visual focus on photorealistic content. Use a concrete shot brief to describe the subject, setting and action that should be visible in the completed sequence.
Write the action as something the viewer can follow. A hand lifting a lemon from a bowl, a bicycle passing a sunlit wall or a bird landing on a branch each provides a clear event with an opening and closing state. Specify which subject carries the scene, what changes during the shot and which detail should remain readable as it moves.
Choose the viewpoint and environment to support that action. A close view can emphasize fingers touching an object, while a wider view can establish the relationship between a person and a location. Include material, lighting and background details when they affect the visible result. Keep the description focused enough that the important movement does not compete with several unrelated events.
The maker’s published Mochi 1 release documents native 480p video generation and describes a photorealistic focus. Plan a scene whose decisive details remain readable at that scale. Fine patterns, small distant faces and precise lettering need separate inspection in the actual output; a convincing overall scene does not establish that every small feature survives motion.
Genmo identifies warping or distortion as a possible issue in extreme motion and notes that the release is less suited to animated styles. For an action-heavy brief, inspect the subject throughout the sequence, particularly where it turns, changes direction or passes behind another object. Select the clip whose visible movement best matches the intended event, then target any specific deformation in the next creative revision.
The maker’s reference implementation exposes controls such as a seed, frame count, inference steps and guidance, alongside the prompt. These describe the reference model workflow; the controls supplied by a particular hosted method are listed with that method. Keep the actual settings used with the resulting clip so a comparison does not depend on an assumed default or on a parameter from a different implementation.
Use the completed footage as a concept shot, realistic scene element or source clip for further editing. Watch the entire sequence for the order and completion of the requested action, continuity of the subject and the usefulness of the final view. A strong opening frame is only one part of a usable moving shot.
Preserve the actual video and its written brief. When the result misses the goal, identify whether the problem is the scene description, a hidden subject detail, an abrupt action or an unsuitable framing choice. Change the relevant part of the prompt while retaining the successful subject and setting. Compare the revision against the same visible goal, using the complete clip rather than a thumbnail to decide whether it serves the intended edit.
", "aboutText": "Mochi 1 is Genmo’s text-to-video model for turning a written scene description into moving imagery. The maker emphasizes motion and prompt adherence, with a visual focus on photorealistic content. Use a concrete shot brief to describe the subject, setting and action that should be visible in the completed sequence.\n\nWrite the action as something the viewer can follow. A hand lifting a lemon from a bowl, a bicycle passing a sunlit wall or a bird landing on a branch each provides a clear event with an opening and closing state. Specify which subject carries the scene, what changes during the shot and which detail should remain readable as it moves.\n\nChoose the viewpoint and environment to support that action. A close view can emphasize fingers touching an object, while a wider view can establish the relationship between a person and a location. Include material, lighting and background details when they affect the visible result. Keep the description focused enough that the important movement does not compete with several unrelated events.\n\nThe maker’s published Mochi 1 release documents native 480p video generation and describes a photorealistic focus. Plan a scene whose decisive details remain readable at that scale. Fine patterns, small distant faces and precise lettering need separate inspection in the actual output; a convincing overall scene does not establish that every small feature survives motion.\n\nGenmo identifies warping or distortion as a possible issue in extreme motion and notes that the release is less suited to animated styles. For an action-heavy brief, inspect the subject throughout the sequence, particularly where it turns, changes direction or passes behind another object. Select the clip whose visible movement best matches the intended event, then target any specific deformation in the next creative revision.\n\nThe maker’s reference implementation exposes controls such as a seed, frame count, inference steps and guidance, alongside the prompt. These describe the reference model workflow; the controls supplied by a particular hosted method are listed with that method. Keep the actual settings used with the resulting clip so a comparison does not depend on an assumed default or on a parameter from a different implementation.\n\nUse the completed footage as a concept shot, realistic scene element or source clip for further editing. Watch the entire sequence for the order and completion of the requested action, continuity of the subject and the usefulness of the final view. A strong opening frame is only one part of a usable moving shot.\n\nPreserve the actual video and its written brief. When the result misses the goal, identify whether the problem is the scene description, a hidden subject detail, an abrupt action or an unsuitable framing choice. Change the relevant part of the prompt while retaining the successful subject and setting. Compare the revision against the same visible goal, using the complete clip rather than a thumbnail to decide whether it serves the intended edit.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "16196d55db947e3ac7fd2a811643a1404301a7892a41bcd2b9e528950df513fb", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "genmo-mochi-v1Mochi 1 is Genmo’s text-to-video model with a focus on realistic imagery, visible motion and adherence to a scene prompt. Prepare a concrete shot description and inspect the completed sequence for action, framing and temporal consistency.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Mochi 1 is Genmo’s text-to-video model for turning a written scene description into moving imagery. The maker emphasizes motion and prompt adherence, with a visual focus on photorealistic content. Use a concrete shot brief to describe the subject, setting and action that should be visible in the completed sequence.
Write the action as something the viewer can follow. A hand lifting a lemon from a bowl, a bicycle passing a sunlit wall or a bird landing on a branch each provides a clear event with an opening and closing state. Specify which subject carries the scene, what changes during the shot and which detail should remain readable as it moves.
Choose the viewpoint and environment to support that action. A close view can emphasize fingers touching an object, while a wider view can establish the relationship between a person and a location. Include material, lighting and background details when they affect the visible result. Keep the description focused enough that the important movement does not compete with several unrelated events.
The maker’s published Mochi 1 release documents native 480p video generation and describes a photorealistic focus. Plan a scene whose decisive details remain readable at that scale. Fine patterns, small distant faces and precise lettering need separate inspection in the actual output; a convincing overall scene does not establish that every small feature survives motion.
Genmo identifies warping or distortion as a possible issue in extreme motion and notes that the release is less suited to animated styles. For an action-heavy brief, inspect the subject throughout the sequence, particularly where it turns, changes direction or passes behind another object. Select the clip whose visible movement best matches the intended event, then target any specific deformation in the next creative revision.
The maker’s reference implementation exposes controls such as a seed, frame count, inference steps and guidance, alongside the prompt. These describe the reference model workflow; the controls supplied by a particular hosted method are listed with that method. Keep the actual settings used with the resulting clip so a comparison does not depend on an assumed default or on a parameter from a different implementation.
Use the completed footage as a concept shot, realistic scene element or source clip for further editing. Watch the entire sequence for the order and completion of the requested action, continuity of the subject and the usefulness of the final view. A strong opening frame is only one part of a usable moving shot.
Preserve the actual video and its written brief. When the result misses the goal, identify whether the problem is the scene description, a hidden subject detail, an abrupt action or an unsuitable framing choice. Change the relevant part of the prompt while retaining the successful subject and setting. Compare the revision against the same visible goal, using the complete clip rather than a thumbnail to decide whether it serves the intended edit.
POST /v1/videostextvideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits genmo-mochi-v1 Conditions: Use the exact Ailoot model selector. | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Conditions: Describe the scene and motion. | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parameteroptional | Contract |
Parametermaterial_types | Contracttext |
Parameterconditions | ContractUse the exact Ailoot model selector., Describe the scene and motion. |
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 $1 per request |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Billing quantity— | Charge Output · Estimated generation cost · Estimate for comparison only $1 estimate before generation This estimate is not an additional charge or a fixed rate for the completed generation. |
Ailoot reserves an estimated amount before a request. After the result, it settles the final charge from measured usage. Streaming settlement uses the final usage record. How reservation and settlement work →
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\ncat > request.json <<'JSON'\n{\n "model": "genmo-mochi-v1",\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 genmo-mochi-v1
/v1/videos/generations