A fast post-trained H3 variant
MiniMax H3 Max is a post-trained variant of the MiniMax H3 base model, optimized around faster generation, prompt adherence and audiovisual quality. The variant was developed through post-training by fal Research. It retains unified multimodal context and natively synchronized picture and sound. Speed is a design priority rather than a fixed completion time for every prompt, duration or application.
Keep Max distinct from the original H3 system and from the separate Max Turbo variant. MiniMax’s current interface lists Max at 480P or 768P, with 768P as the default, 24 frames per second and an integer duration from 5 to 15 seconds. Its documented Max workflow does not offer the original H3 system’s 2K setting or a four-second output.
From a prompt to a shot
Every generation includes a non-empty text brief, up to 7,000 characters per text item. Describe the subject, initial composition, action and result, then make the camera and sound directions clear. For a short object reveal, identify what the viewer should see first, how the object moves into view and how the shot should end.
A useful five-second brief might describe a ceramic cup on a wooden table, a hand placing a saucer beside it, a small camera push and the sound of ceramic meeting wood. Keep the action small enough to fit the selected duration and inspect whether the returned motion and sound follow the same event.
Frame-guided creation
The manufacturer documents an opening frame, an ending frame or both. A first image establishes where the clip begins; a last image establishes the final visual state. Explain the motion connecting them, including changes in pose, object position, camera or lighting. For a two-frame transition, avoid a brief that introduces an incompatible scene between its endpoints.
Frame-guided output derives its aspect ratio from the input image. For text-only work, choose a concrete ratio from 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. Reference-guided work can use an adaptive ratio or one of the documented explicit choices. Compose the reference or written scene for the target frame rather than assume the same arrangement works equally well in portrait and landscape.
Multimodal references
MiniMax’s current Max generation schema also documents reference images, video and audio. State what each should influence: character identity, an environment, a motion pattern, a camera trajectory, voice timbre or a sound characteristic. First/last-frame roles and reference-media roles are mutually exclusive in that interface.
For a character shot, identify the appearance reference and the motion reference separately, then provide the target action and spoken line. A voice reference that establishes delivery is different from copying its complete audio signal. Keep the brief explicit about the features to preserve and the changes to make, and review the actual audiovisual clip against each reference role.
Prompt expansion
The Max-specific expansion setting offers disabled, balanced and quality choices, with balanced as the default. Choose disabled when the supplied brief should pass through without expansion; use a documented expansion mode when additional interpretation is desired. Keep the original brief so a change introduced during expansion can be distinguished from the requested content.
Describe sound as part of the scene. Identify physical sounds, ambience and any spoken words, and separate them from audience-only background music. Provide the exact line and the intended speaker rather than asking for unspecified dialogue. Listen to the result as well as watch it; a convincing image does not establish that the spoken wording or timing is correct.
Input preparation and limits
The current manufacturer schema accepts JPG, JPEG, PNG, WebP, HEIC or HEIF images, up to 30 MB each, with sides from 256 to 5,760 pixels and ratios from 0.4 to 2.5. Opening and ending roles each allow one image; reference mode allows up to nine images. Preserve a clear view of the subject and the details that must remain identifiable.
Reference video permits up to three MP4 or MOV clips, each 2–15 seconds and together at most 15 seconds, with a 50 MB per-file limit. It documents H.264 or H.265 video, AAC or MP3 audio, sides from 256 to 5,760 pixels, ratios from 0.4 to 2.5 and frame rate from 23.976 to 60. Reference audio permits up to three WAV or MP3 clips, each up to 15 MB and 2–15 seconds, together at most 15 seconds. The request body has a separate 64 MB limit.
Use only references that contribute to the shot and identify each contribution in the text. A short, relevant motion clip is easier to use as a direction than a long collection of unrelated events. Keep the intended duration and output resolution explicit so the result can be compared with the same brief.
The finished result
The maker’s asynchronous workflow returns a task identity before the completed video is available. Its task-query interface retrieves tasks from the preceding seven days. Save the actual returned clip and its specification for editing or further review; a task identifier is not the audiovisual artifact. Download addresses are time-limited, so keep the file itself when retaining a selected result.
Review subject continuity, motion, visible text, dialogue and sound timing at the size where the clip will be used. Use concrete feedback for another creative brief: the gesture that changed, the line that was omitted or the framing that needs adjustment. The useful result is a short audiovisual shot tied to the supplied content and its explicit reference relationships.
", "aboutText": "A fast post-trained H3 variant\n\nMiniMax H3 Max is a post-trained variant of the MiniMax H3 base model, optimized around faster generation, prompt adherence and audiovisual quality. The variant was developed through post-training by fal Research. It retains unified multimodal context and natively synchronized picture and sound. Speed is a design priority rather than a fixed completion time for every prompt, duration or application.\n\nKeep Max distinct from the original H3 system and from the separate Max Turbo variant. MiniMax’s current interface lists Max at 480P or 768P, with 768P as the default, 24 frames per second and an integer duration from 5 to 15 seconds. Its documented Max workflow does not offer the original H3 system’s 2K setting or a four-second output.\n\nFrom a prompt to a shot\n\nEvery generation includes a non-empty text brief, up to 7,000 characters per text item. Describe the subject, initial composition, action and result, then make the camera and sound directions clear. For a short object reveal, identify what the viewer should see first, how the object moves into view and how the shot should end.\n\nA useful five-second brief might describe a ceramic cup on a wooden table, a hand placing a saucer beside it, a small camera push and the sound of ceramic meeting wood. Keep the action small enough to fit the selected duration and inspect whether the returned motion and sound follow the same event.\n\nFrame-guided creation\n\nThe manufacturer documents an opening frame, an ending frame or both. A first image establishes where the clip begins; a last image establishes the final visual state. Explain the motion connecting them, including changes in pose, object position, camera or lighting. For a two-frame transition, avoid a brief that introduces an incompatible scene between its endpoints.\n\nFrame-guided output derives its aspect ratio from the input image. For text-only work, choose a concrete ratio from 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. Reference-guided work can use an adaptive ratio or one of the documented explicit choices. Compose the reference or written scene for the target frame rather than assume the same arrangement works equally well in portrait and landscape.\n\nMultimodal references\n\nMiniMax’s current Max generation schema also documents reference images, video and audio. State what each should influence: character identity, an environment, a motion pattern, a camera trajectory, voice timbre or a sound characteristic. First/last-frame roles and reference-media roles are mutually exclusive in that interface.\n\nFor a character shot, identify the appearance reference and the motion reference separately, then provide the target action and spoken line. A voice reference that establishes delivery is different from copying its complete audio signal. Keep the brief explicit about the features to preserve and the changes to make, and review the actual audiovisual clip against each reference role.\n\nPrompt expansion\n\nThe Max-specific expansion setting offers disabled, balanced and quality choices, with balanced as the default. Choose disabled when the supplied brief should pass through without expansion; use a documented expansion mode when additional interpretation is desired. Keep the original brief so a change introduced during expansion can be distinguished from the requested content.\n\nDescribe sound as part of the scene. Identify physical sounds, ambience and any spoken words, and separate them from audience-only background music. Provide the exact line and the intended speaker rather than asking for unspecified dialogue. Listen to the result as well as watch it; a convincing image does not establish that the spoken wording or timing is correct.\n\nInput preparation and limits\n\nThe current manufacturer schema accepts JPG, JPEG, PNG, WebP, HEIC or HEIF images, up to 30 MB each, with sides from 256 to 5,760 pixels and ratios from 0.4 to 2.5. Opening and ending roles each allow one image; reference mode allows up to nine images. Preserve a clear view of the subject and the details that must remain identifiable.\n\nReference video permits up to three MP4 or MOV clips, each 2–15 seconds and together at most 15 seconds, with a 50 MB per-file limit. It documents H.264 or H.265 video, AAC or MP3 audio, sides from 256 to 5,760 pixels, ratios from 0.4 to 2.5 and frame rate from 23.976 to 60. Reference audio permits up to three WAV or MP3 clips, each up to 15 MB and 2–15 seconds, together at most 15 seconds. The request body has a separate 64 MB limit.\n\nUse only references that contribute to the shot and identify each contribution in the text. A short, relevant motion clip is easier to use as a direction than a long collection of unrelated events. Keep the intended duration and output resolution explicit so the result can be compared with the same brief.\n\nThe finished result\n\nThe maker’s asynchronous workflow returns a task identity before the completed video is available. Its task-query interface retrieves tasks from the preceding seven days. Save the actual returned clip and its specification for editing or further review; a task identifier is not the audiovisual artifact. Download addresses are time-limited, so keep the file itself when retaining a selected result.\n\nReview subject continuity, motion, visible text, dialogue and sound timing at the size where the clip will be used. Use concrete feedback for another creative brief: the gesture that changed, the line that was omitted or the framing that needs adjustment. The useful result is a short audiovisual shot tied to the supplied content and its explicit reference relationships.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "7c576e214e08fb68d33c63e8e8e57b3690fd1db92df38a52e9467e2d90a7f6c5", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "minimax/hailuo-3-maxMiniMax H3 Max is a fast post-trained H3 variant for short video with synchronized audio. MiniMax’s documented workflow supports text, frame images and multimodal references, with 480P or 768P output, 5–15-second duration and its own prompt-expansion choices.
This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.
A fast post-trained H3 variant
MiniMax H3 Max is a post-trained variant of the MiniMax H3 base model, optimized around faster generation, prompt adherence and audiovisual quality. The variant was developed through post-training by fal Research. It retains unified multimodal context and natively synchronized picture and sound. Speed is a design priority rather than a fixed completion time for every prompt, duration or application.
Keep Max distinct from the original H3 system and from the separate Max Turbo variant. MiniMax’s current interface lists Max at 480P or 768P, with 768P as the default, 24 frames per second and an integer duration from 5 to 15 seconds. Its documented Max workflow does not offer the original H3 system’s 2K setting or a four-second output.
From a prompt to a shot
Every generation includes a non-empty text brief, up to 7,000 characters per text item. Describe the subject, initial composition, action and result, then make the camera and sound directions clear. For a short object reveal, identify what the viewer should see first, how the object moves into view and how the shot should end.
A useful five-second brief might describe a ceramic cup on a wooden table, a hand placing a saucer beside it, a small camera push and the sound of ceramic meeting wood. Keep the action small enough to fit the selected duration and inspect whether the returned motion and sound follow the same event.
Frame-guided creation
The manufacturer documents an opening frame, an ending frame or both. A first image establishes where the clip begins; a last image establishes the final visual state. Explain the motion connecting them, including changes in pose, object position, camera or lighting. For a two-frame transition, avoid a brief that introduces an incompatible scene between its endpoints.
Frame-guided output derives its aspect ratio from the input image. For text-only work, choose a concrete ratio from 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. Reference-guided work can use an adaptive ratio or one of the documented explicit choices. Compose the reference or written scene for the target frame rather than assume the same arrangement works equally well in portrait and landscape.
Multimodal references
MiniMax’s current Max generation schema also documents reference images, video and audio. State what each should influence: character identity, an environment, a motion pattern, a camera trajectory, voice timbre or a sound characteristic. First/last-frame roles and reference-media roles are mutually exclusive in that interface.
For a character shot, identify the appearance reference and the motion reference separately, then provide the target action and spoken line. A voice reference that establishes delivery is different from copying its complete audio signal. Keep the brief explicit about the features to preserve and the changes to make, and review the actual audiovisual clip against each reference role.
Prompt expansion
The Max-specific expansion setting offers disabled, balanced and quality choices, with balanced as the default. Choose disabled when the supplied brief should pass through without expansion; use a documented expansion mode when additional interpretation is desired. Keep the original brief so a change introduced during expansion can be distinguished from the requested content.
Describe sound as part of the scene. Identify physical sounds, ambience and any spoken words, and separate them from audience-only background music. Provide the exact line and the intended speaker rather than asking for unspecified dialogue. Listen to the result as well as watch it; a convincing image does not establish that the spoken wording or timing is correct.
Input preparation and limits
The current manufacturer schema accepts JPG, JPEG, PNG, WebP, HEIC or HEIF images, up to 30 MB each, with sides from 256 to 5,760 pixels and ratios from 0.4 to 2.5. Opening and ending roles each allow one image; reference mode allows up to nine images. Preserve a clear view of the subject and the details that must remain identifiable.
Reference video permits up to three MP4 or MOV clips, each 2–15 seconds and together at most 15 seconds, with a 50 MB per-file limit. It documents H.264 or H.265 video, AAC or MP3 audio, sides from 256 to 5,760 pixels, ratios from 0.4 to 2.5 and frame rate from 23.976 to 60. Reference audio permits up to three WAV or MP3 clips, each up to 15 MB and 2–15 seconds, together at most 15 seconds. The request body has a separate 64 MB limit.
Use only references that contribute to the shot and identify each contribution in the text. A short, relevant motion clip is easier to use as a direction than a long collection of unrelated events. Keep the intended duration and output resolution explicit so the result can be compared with the same brief.
The finished result
The maker’s asynchronous workflow returns a task identity before the completed video is available. Its task-query interface retrieves tasks from the preceding seven days. Save the actual returned clip and its specification for editing or further review; a task identifier is not the audiovisual artifact. Download addresses are time-limited, so keep the file itself when retaining a selected result.
Review subject continuity, motion, visible text, dialogue and sound timing at the size where the clip will be used. Use concrete feedback for another creative brief: the gesture that changed, the line that was omitted or the framing that needs adjustment. The useful result is a short audiovisual shot tied to the supplied content and its explicit reference relationships.
POST /v1/videostext, imagevideo| Field | Type | Requirement | Values & limits | Default |
|---|---|---|---|---|
Fieldmodel | Typestring | RequirementRequired | Values & limits minimax/hailuo-3-max | Default— |
Fieldprompt | Typestring | RequirementRequired | Values & limits | Default— |
Fieldduration | Typeinteger | RequirementRequired | Values & limits 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 Minimum: 1 Maximum: 600 | Default— |
Fieldresolution | Typestring | RequirementOptional | Values & limits 768p, 480p | Default— |
Fieldaspect_ratio | Typestring | RequirementOptional | Values & limits 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | Default— |
Fieldgenerate_audio | Typeboolean | RequirementOptional | Values & limits false | Default— |
Fieldframe_images | Typearray | RequirementOptional | Values & limits Minimum items: 1 Maximum items: 2 Input content: Array of frame objects. Each object has type=image_url, image_url containing url, and frame_type. Use an HTTPS image URL and set frame_type to first_frame or last_frame. Each frame role appears at most once. Exact keys: type, image_url, frame_type Conditions: These keys describe each frame object; image_url contains only url. Omit frame_images for a text-only request. | Default— |
Fieldinput_references | Typearray | RequirementOptional | Values & limits | Default— |
Fieldcallback_url | Typestring | RequirementOptional | Values & limits Pattern: ^https:// | Default— |
Fieldsession_id | Typestring | RequirementOptional | Values & limits | Default— |
Fieldtrace | Typeobject | RequirementOptional | Values & limits | Default— |
Fielduser | Typestring | RequirementOptional | Values & limits | Default— |
Text to video · A written prompt. · Required: model, prompt, duration
Provide prompt as text and duration as whole seconds. Choose a supported resolution and, if needed, an aspect ratio.
model: Type: string · minimax/hailuo-3-max
prompt: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes
Image to video · A written prompt and a first-frame image. · Required: model, prompt, duration, frame_images
frame_images is an array. Each frame object has type, image_url and frame_type; image_url contains url. Set type to image_url. Use first_frame with an optional last_frame. Each frame role appears at most once. Supply a public HTTPS image URL for each frame. Choose a supported resolution and, if needed, an aspect ratio.
Exact keys: type, image_url, frame_type
model: Type: string · minimax/hailuo-3-max
prompt: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes
| Parameter | Contract |
|---|---|
Parametercontent_type | Contractapplication/json |
Parameterrequired | Contractmodel, prompt, duration |
Parametermaterial_types | Contracttext, image |
Parameteradditional_properties | Contractfalse |
Parameteroptional_controls | Contractresolution, aspect_ratio, generate_audio, frame_images, input_references, callback_url, session_id, trace, user |
Lifecycle: submit_once_poll_original
GET /v1/videos/{public_id}
GET /v1/videos/{public_id}/content
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 component | Billing unit | Billing conditions | Charge |
|---|---|---|---|---|---|---|
| ConfigurationBase token rates | Rate scheduleBase rate | Forecast quantity— | Charge component— | Billing unit— | Billing conditions— | 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 |
| ConfigurationVideo output · reference rate | Rate schedule— | Forecast quantity— | Charge componentreference_output_rate | Billing unitper output second | Billing conditions— | Charge Output · Output video second reference rate · Estimate for comparison only $0.16 per output second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Billing unitper video second | Billing conditionsresolution: 480p | Charge Output · Video price · Estimate for comparison only $0.1 per video second |
| ConfigurationVideo price | Rate schedule— | Forecast quantity— | Charge component— | Billing unitper video second | Billing conditionsresolution: 768p | Charge Output · Video price · Estimate for comparison only $0.16 per video second |
| ConfigurationEstimated generation cost | Rate schedule— | Forecast quantityone generation estimate | Charge component— | Billing unit— | Billing conditions— | Charge Output · Estimated generation cost · Estimate for comparison only $0.5 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 →
Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.
Match each charge to the conditions shown. Use one rate for each set of alternative configurations.
| Configuration | Billing conditions | Charge |
|---|---|---|
| ConfigurationVideo price | Billing conditionsNo additional condition is declared in this pricing key. | Charge Output · Video price $0.16 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsresolution: 480p | Charge Output · Video price $0.1 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
| ConfigurationVideo price | Billing conditionsresolution: 768p | Charge Output · Video price $0.16 per video second Published price reference for the configuration shown. Final charges follow the actual billed configuration. |
set -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_REQUEST'\nfrom pathlib import Path\nPath('request.json').write_text('{"aspect_ratio":"16:9","duration":8,"model":"minimax/hailuo-3-max","prompt":"A serene mountain landscape at sunset","resolution":"480p"}', encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('result.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\nsigned owned content URLs
GET /v1/videos/{public_id}GET /v1/videos/{public_id}/contentset -eu\n: "${AILOOT_API_KEY:?Set your Ailoot API key}"\npython3 - <<'PY_STATUS_URL'\nimport json\nfrom pathlib import Path\nfrom urllib.parse import quote\nr=json.loads(Path('result.json').read_text())\nif not isinstance(r.get('id'),str) or not r['id']:raise SystemExit('Keep the original response and headers for reconciliation; no returned ID')\nPath('status-url.txt').write_text('https://api.ailoot.ai/v1/videos/'+quote(r['id'],safe=''))\nPY_STATUS_URL\ncurl --fail-with-body --silent --show-error "$(cat status-url.txt)" \\\n -H "Authorization: Bearer $AILOOT_API_KEY" -D status-headers.txt -o status.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('status.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\nset -eu\n: "${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())\nif r.get('status')!='completed':raise SystemExit('Keep the original ID and read its status; never recreate an unknown job')\nif not isinstance(r.get('data'),list) or not r['data']:raise SystemExit('Keep the complete original status; no completed outputs supplied')\nurls=[]\nfor i,u in enumerate(r.get('data',[])):\n if not isinstance(u,str):raise SystemExit('Keep the original response; unexpected asset shape')\n urls.append((str(i),u))\nfor label,path in urls:\n u=urljoin('https://api.ailoot.ai',path);z=urlsplit(u)\n if z.scheme!='https' or z.netloc!='api.ailoot.ai' or z.username or z.password:raise SystemExit('Use the actual returned Ailoot owned content URL')\n target=Path('owned-'+label+'.bin')\n subprocess.run(['curl','--fail-with-body','--silent','--show-error',u,'-H','Authorization: Bearer '+os.environ['AILOOT_API_KEY'],'-D',str(target)+'.headers','-o',str(target)],check=True)\nprint('All returned owned URLs saved; complete metadata, timing and usage remain in the JSON.')\nPY_ASSETS\nSave every completed video or returned file; retrieve every actual returned asset URL.
Keep every actual owned output and its returned measured metadata.
503 result_pending_check + originalid + X-Should-Retry:false; never replay original
| Field | Type | Meaning |
|---|---|---|
Fieldindex | Typeinteger | MeaningZero-based position of this video in the outputs list. |
Fieldcontent_url | Typestring | MeaningSigned HTTPS download URL for this completed video. |
Fieldsha256 | Typestring | null | MeaningSHA-256 digest of the original video bytes; null if unavailable. |
Fieldsize_bytes | Typeinteger | null | MeaningSize of the original video file in bytes; null if unavailable. |
Fieldduration_ms | Typeinteger | null | MeaningMeasured video duration in milliseconds; null if unavailable. |
Fieldwidth | Typeinteger | null | MeaningVideo width in pixels; null if unavailable. |
Fieldheight | Typeinteger | null | MeaningVideo height in pixels; null if unavailable. |
Fieldvideo_codec | Typestring | null | MeaningVideo codec identifier; null if not recorded. |
Fieldhas_audio | Typeboolean | null | MeaningWhether the video contains an audio track; null if not measured. |
Fieldaudio_codec | Typestring | null | MeaningAudio codec identifier; null when no identifier is recorded. |
| Response | Condition | Next step |
|---|---|---|
Response404 · not_found_error | ConditionVideo access is unavailable, or this video ID was not found. | Next stepCheck video access. For an existing video, use its original public ID and the same API key. |
Response401 · authentication_error | ConditionThe API key does not match the authenticated account. | Next stepCheck your API key and account access before submitting. |
Response400 · invalid_request_error | ConditionThe request could not be read, or the download index is invalid. | Next stepCorrect the request body. For a download, choose an output index returned by the original task. |
Response422 · price_unavailable | ConditionThe selected video configuration cannot be priced. | Next stepChoose a supported video configuration and complete its required options before submitting a corrected request. |
Response422 · invalid_request_error | ConditionA video input or original continuation task is invalid. | Next stepUse valid HTTPS inputs. For continuation, use your completed original public video ID with the same API key. |
Response402 · billing_error | ConditionThe available balance or limits do not allow a reservation. | Next stepCheck your available balance and limits before sending a new request. |
Response503 · server_error | ConditionVideo verification, storage or service access is temporarily unavailable. | Next stepWait for service availability. If you already have a video ID, check that original task instead of creating another generation. |
Response503 · result_pending_check | ConditionThe original video result and charge need checking. | Next stepKeep the returned video ID and check that task. Do not send a replacement generation request while it is being checked. |
Response503 · owned_result_unavailable | ConditionThe existing video download is temporarily unavailable. | Next stepCheck the same video task later and download its existing output. A new generation creates a separate operation. |
Response409 · video_not_ready | ConditionThe video content has not been published. | Next stepCheck the original task status. Download after it reports completed; if it reports failed, follow its charge-check notice. |
Ailoot Ultra minimax/hailuo-3-max
Use the method paths shown above.