Genmo: Mochi 1

Mochi 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.

Ailoot Ultra · Video POST /v1/videos genmo-mochi-v1

About the model

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.

Ailoot Ultra · Video POST /v1/videos genmo-mochi-v1

genmo-mochi-v1

Genmo /genmo-mochi-v1

Overview

Accepted inputs: Text
Results: Video

Available in Ailoot · inputs & methods

Ailoot Ultra · Video POST /v1/videos

Input types: text
Output types: video

Field	Type	Requirement	Values & limits	Default
Field`model`	Type`string`	RequirementRequired	Values & limits genmo-mochi-v1 Conditions: Use the exact Ailoot model selector.	Default—
Field`prompt`	Type`string`	RequirementRequired	Values & limits Conditions: Describe the scene and motion.	Default—

Method parameters and lifecycle

Parameter	Contract
Parameter`content_type`	Contractapplication/json
Parameter`required`	Contractmodel, prompt
Parameter`optional`	Contract
Parameter`material_types`	Contracttext
Parameter`conditions`	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}

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	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 →

Example requests

Ailoot Ultra · Video

curl · create once and retain receiptRead the original taskSave every completed owned asset

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
cat > request.json <<'JSON'
{
  "model": "genmo-mochi-v1",
  "prompt": "A cat is walking on grass."
}
JSON
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
# Create once; retain id, polling_url, original task identifiers and every header.

set -eu
: "${AILOOT_API_KEY:?Set your Ailoot API key}"
export AILOOT_API_KEY
python3 - <<'PY_STATUS'
import json,os,subprocess
from pathlib import Path
from urllib.parse import urljoin,urlsplit
r=json.loads(Path("result.json").read_text())
u=urljoin("https://api.ailoot.ai",r["polling_url"])
p=urlsplit(u)
if p.scheme!="https" or p.netloc!="api.ailoot.ai" or p.username or p.password:
    raise SystemExit("Unexpected returned polling URL; preserve the response")
subprocess.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)
# Read this same original polling_url again while pending.
# Preserve unknown/result_pending_check; do not repeat creation.
PY_STATUS

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())
roles={}
def visit(v,path=""):
    if isinstance(v,dict):
        for k,x in v.items(): visit(x,path+"/"+k)
    elif isinstance(v,list):
        for i,x in enumerate(v): visit(x,path+"/"+str(i))
    elif isinstance(v,str):
        u=urljoin("https://api.ailoot.ai",v); p=urlsplit(u)
        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"):
            roles.setdefault(u,[]).append(path)
visit(r)
if not roles: raise SystemExit("No completed owned assets; retain the original status")
manifest=[]
for i,(u,paths) in enumerate(roles.items()):
    target=Path(f"asset-{i}.bin")
    subprocess.run(["curl","--fail-with-body","--silent","--show-error",u,"-H","Authorization: Bearer "+os.environ["AILOOT_API_KEY"],"-o",str(target)],check=True)
    raw=target.read_bytes()
    if not raw: raise SystemExit("Empty asset; retain original status and metadata")
    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"
    name=f"asset-{i}.{ext}"
    if target.name!=name: target.rename(name)
    manifest.append({"file":name,"response_paths":paths,"bytes":len(raw)})
Path("asset-manifest.json").write_text(json.dumps(manifest,indent=2))
print("Saved",len(manifest),"unique owned assets; every response role retained")
PY_ASSETS

Receive and save results

Ailoot Ultra · Video

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}

Keep all completed results

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.

If the original response needs checking

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.

Response fields

Field	Type
Field`id`	Typestring
Field`polling_url`	Typestring
Field`provider_task_id`	Typestring
Field`task_id`	Typestring
Field`status`	Typestring
Field`video_url`	Typestring

Aliases

Model aliases

Ailoot Ultra genmo-mochi-v1

Method path aliases

/v1/videos/generations

Related caller IDs

genmo-mochi-v1

FAQ · Genmo: Mochi 1

What inputs and results are available?: POST /v1/videos · genmo-mochi-v1: text → video
Which fields does the request use?: POST /v1/videos · genmo-mochi-v1: model, prompt

Genmo: Mochi 1

Genmo: Mochi 1

Overview

Available in Ailoot · inputs & methods

Pricing

How the final charge is calculated

Estimated rates for comparison

Prices by configuration

Example requests

Ailoot Ultra · Video

Receive and save results

Ailoot Ultra · Video

Keep all completed results

If the original response needs checking

Aliases

Model aliases

Method path aliases

Related caller IDs

The company and its project portfolio

Buy tokens at a discount.

Connect the API to a product you sell.