Hailuo 02 is MiniMax’s video model for text-driven scenes, image animation and a first-and-last-frame workflow. A written brief describes the subject, action and camera, while supplied frame images can establish the visual starting point or the transition’s destination. Choose the generation mode according to the material you already have and the part of the shot you need to control.
For text-to-video, describe a coherent action with a readable setting and viewpoint. A scene might show a small sailing boat passing a pier while the camera follows from shore. Specify what moves, which details should remain visible and how the shot ends. Keep the brief focused on observable events rather than a list of unrelated visual qualities.
For image-to-video, prepare a first frame with the intended subject and framing already established. The maker accepts JPG, JPEG, PNG and WebP images smaller than 20 MB, with a short edge greater than 300 pixels and an aspect ratio between 2:5 and 5:2. Use an image whose important contours and features are visible, then describe the motion to develop from it.
Hailuo 02 also has a documented first-and-last-frame mode. Prepare the two images as the intended opening and closing states of one sequence, and describe how the scene moves between them. The first frame determines the framing; the maker states that a differently sized last frame is cropped to match it. Align the images’ composition in advance when a subject must remain visible through the transition.
The prompt can contain up to 2,000 characters. Hailuo 02 supports bracketed camera commands including push, pull, truck, pan, pedestal, tilt, zoom, tracking and a static shot. Commands placed together in a bracket request simultaneous movement; commands placed at different points in the description request a sequence. The maker recommends combining no more than three movements, so choose the camera action that makes the subject easier to read.
Duration and resolution are linked to the mode. Text-to-video documents six or ten seconds at 768P and six seconds at 1080P. Image-to-video also documents 512P for six or ten seconds. The first-and-last-frame workflow documents 768P for six or ten seconds and 1080P for six seconds. Select a supported combination for the shot instead of transferring one mode’s resolution choices to every other mode.
Automatic prompt optimization is a documented control and is enabled by default in the maker’s workflow. Retain its setting when comparing versions, because a rewritten brief changes what the model receives. Keep the exact text, reference frames and selected output settings with the generated clip so a revision can target the action or framing that needs improvement.
Review the whole completed sequence: the opening composition, continuity of the subject, timing of the action and final frame. For a transition, check both endpoints and the motion between them. Save the actual video for editing, together with the prompt and references; use the next revision to address a concrete visual problem such as an obscured detail, an abrupt camera move or an ending that arrives too early.
", "aboutText": "Hailuo 02 is MiniMax’s video model for text-driven scenes, image animation and a first-and-last-frame workflow. A written brief describes the subject, action and camera, while supplied frame images can establish the visual starting point or the transition’s destination. Choose the generation mode according to the material you already have and the part of the shot you need to control.\n\nFor text-to-video, describe a coherent action with a readable setting and viewpoint. A scene might show a small sailing boat passing a pier while the camera follows from shore. Specify what moves, which details should remain visible and how the shot ends. Keep the brief focused on observable events rather than a list of unrelated visual qualities.\n\nFor image-to-video, prepare a first frame with the intended subject and framing already established. The maker accepts JPG, JPEG, PNG and WebP images smaller than 20 MB, with a short edge greater than 300 pixels and an aspect ratio between 2:5 and 5:2. Use an image whose important contours and features are visible, then describe the motion to develop from it.\n\nHailuo 02 also has a documented first-and-last-frame mode. Prepare the two images as the intended opening and closing states of one sequence, and describe how the scene moves between them. The first frame determines the framing; the maker states that a differently sized last frame is cropped to match it. Align the images’ composition in advance when a subject must remain visible through the transition.\n\nThe prompt can contain up to 2,000 characters. Hailuo 02 supports bracketed camera commands including push, pull, truck, pan, pedestal, tilt, zoom, tracking and a static shot. Commands placed together in a bracket request simultaneous movement; commands placed at different points in the description request a sequence. The maker recommends combining no more than three movements, so choose the camera action that makes the subject easier to read.\n\nDuration and resolution are linked to the mode. Text-to-video documents six or ten seconds at 768P and six seconds at 1080P. Image-to-video also documents 512P for six or ten seconds. The first-and-last-frame workflow documents 768P for six or ten seconds and 1080P for six seconds. Select a supported combination for the shot instead of transferring one mode’s resolution choices to every other mode.\n\nAutomatic prompt optimization is a documented control and is enabled by default in the maker’s workflow. Retain its setting when comparing versions, because a rewritten brief changes what the model receives. Keep the exact text, reference frames and selected output settings with the generated clip so a revision can target the action or framing that needs improvement.\n\nReview the whole completed sequence: the opening composition, continuity of the subject, timing of the action and final frame. For a transition, check both endpoints and the motion between them. Save the actual video for editing, together with the prompt and references; use the next revision to address a concrete visual problem such as an obscured detail, an abrupt camera move or an ending that arrives too early.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "65647926f1f9dd119dfbad893c9b204e070cf299af445e6d478e2d1744771487", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "minimaxi-hailuo-02Hailuo 02 creates video from text or a first-frame image and supports a documented first-and-last-frame workflow. Camera commands, prompt optimization and mode-specific duration and resolution choices help shape the intended shot.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
Hailuo 02 is MiniMax’s video model for text-driven scenes, image animation and a first-and-last-frame workflow. A written brief describes the subject, action and camera, while supplied frame images can establish the visual starting point or the transition’s destination. Choose the generation mode according to the material you already have and the part of the shot you need to control.
For text-to-video, describe a coherent action with a readable setting and viewpoint. A scene might show a small sailing boat passing a pier while the camera follows from shore. Specify what moves, which details should remain visible and how the shot ends. Keep the brief focused on observable events rather than a list of unrelated visual qualities.
For image-to-video, prepare a first frame with the intended subject and framing already established. The maker accepts JPG, JPEG, PNG and WebP images smaller than 20 MB, with a short edge greater than 300 pixels and an aspect ratio between 2:5 and 5:2. Use an image whose important contours and features are visible, then describe the motion to develop from it.
Hailuo 02 also has a documented first-and-last-frame mode. Prepare the two images as the intended opening and closing states of one sequence, and describe how the scene moves between them. The first frame determines the framing; the maker states that a differently sized last frame is cropped to match it. Align the images’ composition in advance when a subject must remain visible through the transition.
The prompt can contain up to 2,000 characters. Hailuo 02 supports bracketed camera commands including push, pull, truck, pan, pedestal, tilt, zoom, tracking and a static shot. Commands placed together in a bracket request simultaneous movement; commands placed at different points in the description request a sequence. The maker recommends combining no more than three movements, so choose the camera action that makes the subject easier to read.
Duration and resolution are linked to the mode. Text-to-video documents six or ten seconds at 768P and six seconds at 1080P. Image-to-video also documents 512P for six or ten seconds. The first-and-last-frame workflow documents 768P for six or ten seconds and 1080P for six seconds. Select a supported combination for the shot instead of transferring one mode’s resolution choices to every other mode.
Automatic prompt optimization is a documented control and is enabled by default in the maker’s workflow. Retain its setting when comparing versions, because a rewritten brief changes what the model receives. Keep the exact text, reference frames and selected output settings with the generated clip so a revision can target the action or framing that needs improvement.
Review the whole completed sequence: the opening composition, continuity of the subject, timing of the action and final frame. For a transition, check both endpoints and the motion between them. Save the actual video for editing, together with the prompt and references; use the next revision to address a concrete visual problem such as an obscured detail, an abrupt camera move or an ending that arrives too early.
POST /v1/videostext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits minimaxi-hailuo-02 Conditions: Use the exact Ailoot model selector. | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits Conditions: Describe the scene and motion. | Default— |
Fieldduration | Typeinteger | RequirementOptional | Values & limits 6, 10 Conditions: Send one of the listed duration values; no default is asserted. | Default— |
Fieldend_image | Typestring | RequirementOptional | Values & limits Conditions: An end frame applies only in a supported image input mode. | Default— |
Fieldimage | Typestring or array<string> | RequirementOptional | Values & limits Conditions: Use an actual publicly reachable image URL or a base64 image string; no maximum image count is asserted here. | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 512P, 768P, 1080P Conditions: Send one of the listed resolution values; no default is asserted. | Default— |
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt |
Parameteroptional | Contractduration, end_image, image, resolution |
Parametermaterial_types | Contracttext, image |
Parameterconditions | ContractUse the exact Ailoot model selector., Describe the scene and motion., Send one of the listed duration values; no default is asserted., An end frame applies only in a supported image input mode., Use an actual publicly reachable image URL or a base64 image string; no maximum image count is asserted here., Send one of the listed resolution values; no default is asserted. |
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": "minimaxi-hailuo-02",\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 minimaxi-hailuo-02
/v1/videos/generations