{ "aboutHtml": "

One audiovisual result from a multimodal brief

MiniMax H3 is MiniMax’s omni-modal video system. It interprets text, images, video and audio together, then generates video with native stereo sound. The maker presents it for short creative work such as product visuals, advertising, animated posters and film-title concepts, where the relationships among reference assets matter as much as the scene description.

The documented system produces 4–15-second video at 24 frames per second with 32 kHz stereo audio. Its H3-Base generation operates at 768p; the full 2K workflow regenerates that result using the original multimodal context. This is more than a conventional resize: the second stage uses the model and source context again to recover fine detail. H3 Max and H3-Context-IR have separate roles and limits.

Text and frame-guided creation

Text-only input describes the complete audiovisual timeline. A first image anchors the opening, a last image anchors the ending, and two images can define both. For a first-frame shot, begin with the composition and identity visible in the still, then describe the action developing from it. For a first-to-last-frame transition, describe the observable movement connecting the two states rather than repeat two unrelated image descriptions.

A practical product brief can specify a closed package in the opening frame, the hand that opens it, the camera’s gentle movement and the final state to reach. Preserve the object’s shape, label placement and lighting in the supplied frames. Frame-guided creation and reference-guided creation are separate input modes; the maker’s interface does not mix first/last-frame roles with reference-media roles in one request.

Reference-guided generation and editing

The reference mode accepts text with images, video clips and audio clips. Identify what each source contributes: a character’s appearance, a location, camera motion, the temporal structure of a source clip or a voice. A video used only for camera movement is different from a video that should actually be edited or continued. State that relationship explicitly.

The maker’s reference guide separates subject definitions, a task summary, retention analysis, a detailed shot description, overall soundscape and audience-only background music. It distinguishes preservation of visible content from attribute transfer or a broad style reference. For audio, copying a signal is different from referencing timbre, rhythm or delivery. Keep those roles stable throughout the brief.

For a reference-driven scene, supply a character image, a short camera-movement reference and an audio voice reference, then describe where each should affect the target shot. State which clothing, environment or object details must remain recognizable. Compare the finished clip with those requirements, including motion continuity and the relationship between the visible speaker and the voice heard.

Speech, sound and shot timing

H3 jointly models dialogue, physical sounds, ambience and music. The model card documents stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish; other languages are described as varying in support. Provide the exact spoken words and language, with a stable speaker identity across shots.

The maker’s prompt-writing guides use English for descriptive sections while preserving dialogue and visible text in their original language. Spoken content uses <d>[Language] ...</d>, with speaker identity and voice description outside the block. Distinguish physical speech from off-screen voiceover, and identify when a line continues across a cut or is cut off by the end. Preserve visible text exactly as well. Fit the amount of speech to the chosen duration and inspect the rendered words and audible line together.

Describe camera movement as an action, including its range and speed when they matter. Number shots in playback order and keep cut times within the video duration. Separate scene sounds such as footsteps or a door closing from background score audible only to the audience. These choices make a short shot plan easier to interpret and easier to review against its result.

Input preparation and numerical limits

The current generation schema requires non-empty text in every mode, with up to 7,000 characters per text item. Images can be JPG, JPEG, PNG, WebP, HEIC or HEIF, up to 30 MB each, with each side from 256 to 5,760 pixels and aspect ratio from 0.4 to 2.5. Frame input permits one opening and one ending image; reference mode permits up to nine reference images.

Reference video can contain up to three MP4 or MOV clips, each 2–15 seconds and together no more than 15 seconds. A clip can be up to 50 MB; its video codec is H.264 or H.265, with 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 supports up to three WAV or MP3 clips, up to 15 MB each, each 2–15 seconds and together no more than 15 seconds. The model card caps mixed reference inputs at 12 files. The documented request-body limit is 64 MB, distinct from the per-file limits.

Choose only references that contribute to the brief and make every contribution explicit. A clear subject view is more useful than several conflicting views with no explanation. Preserve reference order, crop away irrelevant material without removing necessary scene context and check that short source clips contain the action or voice characteristic being requested.

Output shape and the complete system

The manufacturer’s H3 interface offers 768P and 2K. Text-only generation requires a concrete ratio: 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. First/last-frame creation takes its aspect ratio from the input image; reference creation can use an adaptive or explicit ratio. Integer output duration is 4–15 seconds.

The model card distinguishes H3-Context-IR, which interprets and enriches the brief, H3-Base, which generates audiovisual content, and H3-Regenerate-2K, which creates the higher-resolution result. The released base checkpoints separate frame-guided and omni-reference tasks. The context and regeneration components are distinct from those base weights, so the name of an open checkpoint alone does not establish the whole system’s behavior.

The maker’s generation workflow is asynchronous. Its task-query interface retrieves tasks from the preceding seven days. Keep the task identity until the actual video result is returned, then save the clip rather than retain only a time-limited download address. Review visual identity, small text, object interactions, spoken content and sound timing at the intended viewing size. The manufacturer identifies multimodal understanding and fine visual detail as continuing areas for improvement; a detailed brief and source comparison remain central to a useful result.

", "aboutText": "One audiovisual result from a multimodal brief\n\nMiniMax H3 is MiniMax’s omni-modal video system. It interprets text, images, video and audio together, then generates video with native stereo sound. The maker presents it for short creative work such as product visuals, advertising, animated posters and film-title concepts, where the relationships among reference assets matter as much as the scene description.\n\nThe documented system produces 4–15-second video at 24 frames per second with 32 kHz stereo audio. Its H3-Base generation operates at 768p; the full 2K workflow regenerates that result using the original multimodal context. This is more than a conventional resize: the second stage uses the model and source context again to recover fine detail. H3 Max and H3-Context-IR have separate roles and limits.\n\nText and frame-guided creation\n\nText-only input describes the complete audiovisual timeline. A first image anchors the opening, a last image anchors the ending, and two images can define both. For a first-frame shot, begin with the composition and identity visible in the still, then describe the action developing from it. For a first-to-last-frame transition, describe the observable movement connecting the two states rather than repeat two unrelated image descriptions.\n\nA practical product brief can specify a closed package in the opening frame, the hand that opens it, the camera’s gentle movement and the final state to reach. Preserve the object’s shape, label placement and lighting in the supplied frames. Frame-guided creation and reference-guided creation are separate input modes; the maker’s interface does not mix first/last-frame roles with reference-media roles in one request.\n\nReference-guided generation and editing\n\nThe reference mode accepts text with images, video clips and audio clips. Identify what each source contributes: a character’s appearance, a location, camera motion, the temporal structure of a source clip or a voice. A video used only for camera movement is different from a video that should actually be edited or continued. State that relationship explicitly.\n\nThe maker’s reference guide separates subject definitions, a task summary, retention analysis, a detailed shot description, overall soundscape and audience-only background music. It distinguishes preservation of visible content from attribute transfer or a broad style reference. For audio, copying a signal is different from referencing timbre, rhythm or delivery. Keep those roles stable throughout the brief.\n\nFor a reference-driven scene, supply a character image, a short camera-movement reference and an audio voice reference, then describe where each should affect the target shot. State which clothing, environment or object details must remain recognizable. Compare the finished clip with those requirements, including motion continuity and the relationship between the visible speaker and the voice heard.\n\nSpeech, sound and shot timing\n\nH3 jointly models dialogue, physical sounds, ambience and music. The model card documents stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish; other languages are described as varying in support. Provide the exact spoken words and language, with a stable speaker identity across shots.\n\nThe maker’s prompt-writing guides use English for descriptive sections while preserving dialogue and visible text in their original language. Spoken content uses `[Language] ...`, with speaker identity and voice description outside the block. Distinguish physical speech from off-screen voiceover, and identify when a line continues across a cut or is cut off by the end. Preserve visible text exactly as well. Fit the amount of speech to the chosen duration and inspect the rendered words and audible line together.\n\nDescribe camera movement as an action, including its range and speed when they matter. Number shots in playback order and keep cut times within the video duration. Separate scene sounds such as footsteps or a door closing from background score audible only to the audience. These choices make a short shot plan easier to interpret and easier to review against its result.\n\nInput preparation and numerical limits\n\nThe current generation schema requires non-empty text in every mode, with up to 7,000 characters per text item. Images can be JPG, JPEG, PNG, WebP, HEIC or HEIF, up to 30 MB each, with each side from 256 to 5,760 pixels and aspect ratio from 0.4 to 2.5. Frame input permits one opening and one ending image; reference mode permits up to nine reference images.\n\nReference video can contain up to three MP4 or MOV clips, each 2–15 seconds and together no more than 15 seconds. A clip can be up to 50 MB; its video codec is H.264 or H.265, with 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 supports up to three WAV or MP3 clips, up to 15 MB each, each 2–15 seconds and together no more than 15 seconds. The model card caps mixed reference inputs at 12 files. The documented request-body limit is 64 MB, distinct from the per-file limits.\n\nChoose only references that contribute to the brief and make every contribution explicit. A clear subject view is more useful than several conflicting views with no explanation. Preserve reference order, crop away irrelevant material without removing necessary scene context and check that short source clips contain the action or voice characteristic being requested.\n\nOutput shape and the complete system\n\nThe manufacturer’s H3 interface offers 768P and 2K. Text-only generation requires a concrete ratio: 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. First/last-frame creation takes its aspect ratio from the input image; reference creation can use an adaptive or explicit ratio. Integer output duration is 4–15 seconds.\n\nThe model card distinguishes H3-Context-IR, which interprets and enriches the brief, H3-Base, which generates audiovisual content, and H3-Regenerate-2K, which creates the higher-resolution result. The released base checkpoints separate frame-guided and omni-reference tasks. The context and regeneration components are distinct from those base weights, so the name of an open checkpoint alone does not establish the whole system’s behavior.\n\nThe maker’s generation workflow is asynchronous. Its task-query interface retrieves tasks from the preceding seven days. Keep the task identity until the actual video result is returned, then save the clip rather than retain only a time-limited download address. Review visual identity, small text, object interactions, spoken content and sound timing at the intended viewing size. The manufacturer identifies multimodal understanding and fine visual detail as continuing areas for improvement; a detailed brief and source comparison remain central to a useful result.", "editorialOverlay": { "copy_fields": null, "copy_sha256": null, "copy_source": null, "html_sha256": "2a732ef30bbe7d9e1e5f9e0cb55ff37796f87542a8d9d6abf8d27a74810d8f67", "module_sha256": "ee9dc1c50b1e6a8fb7fa062030fcb4646b9aaaeb08be513b723a5a92a7290f06", "raw_model_unchanged": true, "schema": "ailoot-native-model-editorial-v1" }, "locale": "en", "methods": [ { "html": "
MM

MiniMax: H3

MiniMax /minimax/hailuo-3

Overview

MiniMax H3 generates short video with native stereo audio from text, frame images or multimodal references. It supports first/last-frame creation, reference-guided editing and motion or voice relationships, with 4–15-second output and a distinct 2K regeneration workflow.

Accepted inputs
Text · Images · Audio · Video
Results
Video
About the model

This description covers the model’s capabilities. Available in Ailoot inputs, outputs and options are listed for the selected method below.

One audiovisual result from a multimodal brief

MiniMax H3 is MiniMax’s omni-modal video system. It interprets text, images, video and audio together, then generates video with native stereo sound. The maker presents it for short creative work such as product visuals, advertising, animated posters and film-title concepts, where the relationships among reference assets matter as much as the scene description.

The documented system produces 4–15-second video at 24 frames per second with 32 kHz stereo audio. Its H3-Base generation operates at 768p; the full 2K workflow regenerates that result using the original multimodal context. This is more than a conventional resize: the second stage uses the model and source context again to recover fine detail. H3 Max and H3-Context-IR have separate roles and limits.

Text and frame-guided creation

Text-only input describes the complete audiovisual timeline. A first image anchors the opening, a last image anchors the ending, and two images can define both. For a first-frame shot, begin with the composition and identity visible in the still, then describe the action developing from it. For a first-to-last-frame transition, describe the observable movement connecting the two states rather than repeat two unrelated image descriptions.

A practical product brief can specify a closed package in the opening frame, the hand that opens it, the camera’s gentle movement and the final state to reach. Preserve the object’s shape, label placement and lighting in the supplied frames. Frame-guided creation and reference-guided creation are separate input modes; the maker’s interface does not mix first/last-frame roles with reference-media roles in one request.

Reference-guided generation and editing

The reference mode accepts text with images, video clips and audio clips. Identify what each source contributes: a character’s appearance, a location, camera motion, the temporal structure of a source clip or a voice. A video used only for camera movement is different from a video that should actually be edited or continued. State that relationship explicitly.

The maker’s reference guide separates subject definitions, a task summary, retention analysis, a detailed shot description, overall soundscape and audience-only background music. It distinguishes preservation of visible content from attribute transfer or a broad style reference. For audio, copying a signal is different from referencing timbre, rhythm or delivery. Keep those roles stable throughout the brief.

For a reference-driven scene, supply a character image, a short camera-movement reference and an audio voice reference, then describe where each should affect the target shot. State which clothing, environment or object details must remain recognizable. Compare the finished clip with those requirements, including motion continuity and the relationship between the visible speaker and the voice heard.

Speech, sound and shot timing

H3 jointly models dialogue, physical sounds, ambience and music. The model card documents stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish; other languages are described as varying in support. Provide the exact spoken words and language, with a stable speaker identity across shots.

The maker’s prompt-writing guides use English for descriptive sections while preserving dialogue and visible text in their original language. Spoken content uses <d>[Language] ...</d>, with speaker identity and voice description outside the block. Distinguish physical speech from off-screen voiceover, and identify when a line continues across a cut or is cut off by the end. Preserve visible text exactly as well. Fit the amount of speech to the chosen duration and inspect the rendered words and audible line together.

Describe camera movement as an action, including its range and speed when they matter. Number shots in playback order and keep cut times within the video duration. Separate scene sounds such as footsteps or a door closing from background score audible only to the audience. These choices make a short shot plan easier to interpret and easier to review against its result.

Input preparation and numerical limits

The current generation schema requires non-empty text in every mode, with up to 7,000 characters per text item. Images can be JPG, JPEG, PNG, WebP, HEIC or HEIF, up to 30 MB each, with each side from 256 to 5,760 pixels and aspect ratio from 0.4 to 2.5. Frame input permits one opening and one ending image; reference mode permits up to nine reference images.

Reference video can contain up to three MP4 or MOV clips, each 2–15 seconds and together no more than 15 seconds. A clip can be up to 50 MB; its video codec is H.264 or H.265, with 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 supports up to three WAV or MP3 clips, up to 15 MB each, each 2–15 seconds and together no more than 15 seconds. The model card caps mixed reference inputs at 12 files. The documented request-body limit is 64 MB, distinct from the per-file limits.

Choose only references that contribute to the brief and make every contribution explicit. A clear subject view is more useful than several conflicting views with no explanation. Preserve reference order, crop away irrelevant material without removing necessary scene context and check that short source clips contain the action or voice characteristic being requested.

Output shape and the complete system

The manufacturer’s H3 interface offers 768P and 2K. Text-only generation requires a concrete ratio: 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. First/last-frame creation takes its aspect ratio from the input image; reference creation can use an adaptive or explicit ratio. Integer output duration is 4–15 seconds.

The model card distinguishes H3-Context-IR, which interprets and enriches the brief, H3-Base, which generates audiovisual content, and H3-Regenerate-2K, which creates the higher-resolution result. The released base checkpoints separate frame-guided and omni-reference tasks. The context and regeneration components are distinct from those base weights, so the name of an open checkpoint alone does not establish the whole system’s behavior.

The maker’s generation workflow is asynchronous. Its task-query interface retrieves tasks from the preceding seven days. Keep the task identity until the actual video result is returned, then save the clip rather than retain only a time-limited download address. Review visual identity, small text, object interactions, spoken content and sound timing at the intended viewing size. The manufacturer identifies multimodal understanding and fine visual detail as continuing areas for improvement; a detailed brief and source comparison remain central to a useful result.

Available in Ailoot · inputs & methods

Ailoot Ultra · Video POST /v1/videos
Input types
text, image, audio, video
Output types
video
Output format
original MP4 bytes; no normalization/transcode
FieldTypeRequirementValues & limitsDefault
FieldmodelTypestringRequirementRequiredValues & limits
minimax/hailuo-3
Default—
FieldpromptTypestringRequirementRequiredValues & limitsDefault—
FielddurationTypeintegerRequirementRequiredValues & limits
5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15
Minimum: 1
Maximum: 600
Default—
FieldresolutionTypestringRequirementOptionalValues & limits
2K
Default—
Fieldaspect_ratioTypestringRequirementOptionalValues & limits
21:9, 16:9, 4:3, 1:1, 3:4, 9:16
Default—
Fieldgenerate_audioTypebooleanRequirementOptionalValues & limits
false, true
Default—
Fieldframe_imagesTypearrayRequirementOptionalValues & 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_referencesTypearrayRequirementOptionalValues & limitsDefault—
Fieldcallback_urlTypestringRequirementOptionalValues & limits
Pattern: ^https://
Default—
Fieldsession_idTypestringRequirementOptionalValues & limitsDefault—
FieldtraceTypeobjectRequirementOptionalValues & limitsDefault—
FielduserTypestringRequirementOptionalValues & limitsDefault—
Input material combinations

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

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. Use frame images or image references in one request; do not combine both. Choose a supported resolution and, if needed, an aspect ratio.

Exact keys: type, image_url, frame_type

model: Type: string · minimax/hailuo-3

prompt: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes

Reference to video · A written prompt and supported image, video, audio references. · Required: model, prompt, duration, input_references

input_references is an array of objects. Set type to image_url, video_url, audio_url, and use the matching field containing url. Use public HTTPS URLs. Omit frame_images to select reference mode. The estimate includes the displayed per-image component only for image references after the first five. Final charge follows the actual billed configuration. Do not combine image references with frame images. Choose a supported resolution and, if needed, an aspect ratio.

model: Type: string · minimax/hailuo-3

prompt: Type: string · Maximum UTF-8 bytes: 10,000 · Non-whitespace required: Yes

Method parameters and lifecycle
ParameterContract
Parametercontent_typeContractapplication/json
ParameterrequiredContractmodel, prompt, duration
Parametermaterial_typesContracttext, image, audio, video
Parameteradditional_propertiesContractfalse
Parameteroptional_controlsContractresolution, 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

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.

ConfigurationRate scheduleForecast quantityBilling unitBilling conditionsCharge
ConfigurationBase token ratesRate scheduleBase rateForecast quantity—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 priceRate schedule—Forecast quantity—Billing unitper video secondBilling conditionsNo additional condition is declared in this pricing key.Charge
Output · Video price · Estimate for comparison only $0.26 per video second
Configurationreference imageRate schedule—Forecast quantity—Billing unitper reference imageBilling conditions—Charge
Input · reference image · Estimate for comparison only $0.08 per reference image
ConfigurationEstimated generation costRate schedule—Forecast quantityone generation estimateBilling unit—Billing conditions—Charge
Output · Estimated generation cost · Estimate for comparison only $1.3 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 →

Reference tariff details

Model-level reference schedules do not change method selection, quotes or charges. Active charges use the selected Ailoot method rates.

Video configuration price references

Prices by configuration

Match each charge to the conditions shown. Use one rate for each set of alternative configurations.

ConfigurationBilling conditionsCharge
ConfigurationVideo priceBilling conditionsNo additional condition is declared in this pricing key.Charge
Output · Video price $0.26 per video second

Published price reference for the configuration shown. Final charges follow the actual billed configuration.

ConfigurationReference images after the first fiveBilling conditionsNo additional condition is declared in this pricing key.Charge
Input · Reference images after the first five $0.08 per image

The first five reference images are free; the listed per-image rate applies after the first five. Published price reference for the configuration shown. Final charges follow the actual billed configuration.

Example requests

Ailoot Ultra · Video

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","prompt":"A serene mountain landscape at sunset","resolution":"2K"}', 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\n

Receive and save results

Ailoot Ultra · Video

signed owned content URLs

Check job status
set -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 $AILOOT_API_KEY" -D status-headers.txt -o status.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('status.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\n
Other content reads
set -eu\n: "${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\n
Keep all completed results

Save every completed video or returned file; retrieve every actual returned asset URL.

Keep every actual owned output and its returned measured metadata.

If the original response needs checking

503 result_pending_check + originalid + X-Should-Retry:false; never replay original

Response fields
FieldTypeMeaning
FieldindexTypeintegerMeaningZero-based position of this video in the outputs list.
Fieldcontent_urlTypestringMeaningSigned HTTPS download URL for this completed video.
Fieldsha256Typestring | nullMeaningSHA-256 digest of the original video bytes; null if unavailable.
Fieldsize_bytesTypeinteger | nullMeaningSize of the original video file in bytes; null if unavailable.
Fieldduration_msTypeinteger | nullMeaningMeasured video duration in milliseconds; null if unavailable.
FieldwidthTypeinteger | nullMeaningVideo width in pixels; null if unavailable.
FieldheightTypeinteger | nullMeaningVideo height in pixels; null if unavailable.
Fieldvideo_codecTypestring | nullMeaningVideo codec identifier; null if not recorded.
Fieldhas_audioTypeboolean | nullMeaningWhether the video contains an audio track; null if not measured.
Fieldaudio_codecTypestring | nullMeaningAudio codec identifier; null when no identifier is recorded.
Errors and next steps
ResponseConditionNext step
Response404 · not_found_errorConditionVideo 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_errorConditionThe API key does not match the authenticated account.Next stepCheck your API key and account access before submitting.
Response400 · invalid_request_errorConditionThe 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_unavailableConditionThe 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_errorConditionA 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_errorConditionThe available balance or limits do not allow a reservation.Next stepCheck your available balance and limits before sending a new request.
Response503 · server_errorConditionVideo 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_checkConditionThe 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_unavailableConditionThe 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_readyConditionThe 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.

Aliases

Model aliases

Ailoot Ultra minimax/hailuo-3

Method path aliases

Use the method paths shown above.

Related caller IDs

minimax/hailuo-3

", "method_identity": { "effective_request_model_id": "minimax/hailuo-3", "fmt": "videos", "http": "POST", "path": "/v1/videos", "request_model_id": "minimax/hailuo-3", "route_label": "Ultra" }, "method_key": "Ultra|videos|/v1/videos|minimax%2Fhailuo-3", "ordinal": 0, "rawMethod": { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "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.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every actual owned output and its returned measured metadata.", "defaults": { "aspect_ratio": null, "duration": null, "generate_audio": "endpoint capability flag when published; omitted unknown stays unknown; never guarantees audio track", "resolution": null, "seed": null, "size": null, "wire_omissions_preserved": true }, "errors": [ { "condition": "Video access is unavailable, or this video ID was not found.", "http_status": 404, "public_identifier_field": "error.type", "recovery": "Check video access. For an existing video, use its original public ID and the same API key.", "type": "not_found_error" }, { "condition": "The API key does not match the authenticated account.", "http_status": 401, "public_identifier_field": "error.type", "recovery": "Check your API key and account access before submitting.", "type": "authentication_error" }, { "condition": "The request could not be read, or the download index is invalid.", "http_status": 400, "public_identifier_field": "error.type", "recovery": "Correct the request body. For a download, choose an output index returned by the original task.", "type": "invalid_request_error" }, { "condition": "The selected video configuration cannot be priced.", "http_status": 422, "public_identifier_field": "error.type", "recovery": "Choose a supported video configuration and complete its required options before submitting a corrected request.", "type": "price_unavailable" }, { "condition": "A video input or original continuation task is invalid.", "http_status": 422, "public_identifier_field": "error.type", "recovery": "Use valid HTTPS inputs. For continuation, use your completed original public video ID with the same API key.", "type": "invalid_request_error" }, { "condition": "The available balance or limits do not allow a reservation.", "http_status": 402, "public_identifier_field": "error.type", "recovery": "Check your available balance and limits before sending a new request.", "type": "billing_error" }, { "condition": "Video verification, storage or service access is temporarily unavailable.", "http_status": 503, "public_identifier_field": "error.type", "recovery": "Wait for service availability. If you already have a video ID, check that original task instead of creating another generation.", "type": "server_error" }, { "code": "result_pending_check", "condition": "The original video result and charge need checking.", "http_status": 503, "public_identifier_field": "error.code", "recovery": "Keep the returned video ID and check that task. Do not send a replacement generation request while it is being checked.", "type": "server_error" }, { "code": "owned_result_unavailable", "condition": "The existing video download is temporarily unavailable.", "http_status": 503, "public_identifier_field": "error.code", "recovery": "Check the same video task later and download its existing output. A new generation creates a separate operation.", "type": "server_error" }, { "condition": "The video content has not been published.", "http_status": 409, "public_identifier_field": "error.type", "recovery": "Check the original task status. Download after it reports completed; if it reports failed, follow its charge-check notice.", "type": "video_not_ready" } ], "hints": [ "No null values or duplicate keys at any JSON object level", "No duration/resolution/aspect default is inserted", "Prompt required for all21 despite broader official image-only schema", "A request must also pass model membership, exact price card, SKU selection and frozen quote construction", "Non-string known trace fields reject; other trace keys retain arbitrary JSON", "No n/output-count/client price fields accepted", "Provider passthrough disabled for all21; feed allowlist names do not supply provider slug/value contract" ], "ignored_fields": [], "lifecycle": { "cancel_endpoint": null, "content": [ { "http": "GET", "path": "/v1/videos/{public_id}/content", "query": { "index": "actual output index" } } ], "create": { "http": "POST", "path": "/v1/videos" }, "mode": "submit_once_poll_original", "public_id": "video_; owner user/key/group scope", "status": [ { "http": "GET", "path": "/v1/videos/{public_id}" } ], "submit_status": 202, "terminal_failure_public": "200 failed + charge_pending_check=true; inspect original operation", "terminal_provider_states": [ "failed", "cancelled", "expired" ], "unknown": "503 result_pending_check + originalid + X-Should-Retry:false; never replay original" }, "material_combinations": [ { "mode": "text_to_video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "Provide prompt as text and duration as whole seconds. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration" ], "required_material": "A written prompt." }, { "exact_keys": [ "type", "image_url", "frame_type" ], "mode": "image_to_video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "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. Use frame images or image references in one request; do not combine both. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration", "frame_images" ], "required_material": "A written prompt and a first-frame image." }, { "mode": "Reference to video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "input_references is an array of objects. Set type to image_url, video_url, audio_url, and use the matching field containing url. Use public HTTPS URLs. Omit frame_images to select reference mode. The estimate includes the displayed per-image component only for image references after the first five. Final charge follows the actual billed configuration. Do not combine image references with frame images. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration", "input_references" ], "required_material": "A written prompt and supported image, video, audio references." } ], "operation_modes": [ "text_to_video", "image_to_video_frame_images", "reference_to_video" ], "outputs": { "content_range_supported": true, "every_actual_output": true, "family": "video", "fields": [ { "condition": "Always present for each completed output.", "description": "Zero-based position of this video in the outputs list.", "field_path": "outputs[].index", "json_schema": { "type": "integer" }, "name": "index", "nullable": false, "type": "integer" }, { "condition": "Present after the owned result is available and a signed URL is created.", "description": "Signed HTTPS download URL for this completed video.", "field_path": "outputs[].content_url", "json_schema": { "type": "string" }, "name": "content_url", "nullable": false, "type": "string" }, { "condition": "A nonempty recorded digest is returned; otherwise null.", "description": "SHA-256 digest of the original video bytes; null if unavailable.", "field_path": "outputs[].sha256", "json_schema": { "type": [ "string", "null" ] }, "name": "sha256", "nullable": true, "type": "string | null" }, { "condition": "Returned when the recorded file size is positive.", "description": "Size of the original video file in bytes; null if unavailable.", "field_path": "outputs[].size_bytes", "json_schema": { "type": [ "integer", "null" ] }, "name": "size_bytes", "nullable": true, "type": "integer | null" }, { "condition": "Returned when the measured duration is positive.", "description": "Measured video duration in milliseconds; null if unavailable.", "field_path": "outputs[].duration_ms", "json_schema": { "type": [ "integer", "null" ] }, "name": "duration_ms", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video width in pixels; null if unavailable.", "field_path": "outputs[].width", "json_schema": { "type": [ "integer", "null" ] }, "name": "width", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video height in pixels; null if unavailable.", "field_path": "outputs[].height", "json_schema": { "type": [ "integer", "null" ] }, "name": "height", "nullable": true, "type": "integer | null" }, { "condition": "Returned together with positive recorded width and height.", "description": "Video codec identifier; null if not recorded.", "field_path": "outputs[].video_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "video_codec", "nullable": true, "type": "string | null" }, { "condition": "Returned when width, height and the video codec are recorded; false is a known result.", "description": "Whether the video contains an audio track; null if not measured.", "field_path": "outputs[].has_audio", "json_schema": { "type": [ "boolean", "null" ] }, "name": "has_audio", "nullable": true, "type": "boolean | null" }, { "condition": "Returned when video metadata is recorded and the audio codec identifier is nonempty.", "description": "Audio codec identifier; null when no identifier is recorded.", "field_path": "outputs[].audio_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "audio_codec", "nullable": true, "type": "string | null" } ], "format": "original MP4 bytes; no normalization/transcode", "max_aggregate_seconds": 2400, "max_bytes_per_output": 67108864, "max_seconds_per_output": 600, "result": "signed owned content URLs", "unmeasured_fields_nullable": true }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "minimax/hailuo-3" ], "enum_known": true, "name": "model", "required": true, "schema": { "const": "minimax/hailuo-3" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minLength": 1, "name": "prompt", "required": true, "schema": { "minLength": 1, "type": "string", "x-source-max-utf8-bytes": 10000, "x-source-non-whitespace": true }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "enum_known": true, "maximum": 600, "minimum": 1, "name": "duration", "required": true, "schema": { "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "maximum": 600, "minimum": 1, "type": "integer" }, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "2K" ], "enum_known": true, "name": "resolution", "required": false, "schema": { "enum": [ "2K" ] }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ], "enum_known": true, "name": "aspect_ratio", "required": false, "schema": { "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ false, true ], "enum_known": true, "name": "generate_audio", "required": false, "schema": { "enum": [ false, true ], "x-omitted-default": "published audio capability when true/false; unknown if null; output audio must be measured" }, "type": "boolean" }, { "availability": "source_interface", "conditions": "These keys describe each frame object; image_url contains only url. Omit frame_images for a text-only request.", "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.", "default": null, "default_known": false, "enum": null, "enum_known": false, "exact_keys": [ "type", "image_url", "frame_type" ], "maxItems": 2, "max_items": 2, "minItems": 1, "min_items": 1, "name": "frame_images", "required": false, "schema": { "items": { "additionalProperties": false, "properties": { "frame_type": { "enum": [ "first_frame", "last_frame" ] }, "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url", "frame_type" ], "type": "object" }, "maxItems": 2, "minItems": 1, "type": "array", "x-source-unique-role": "frame_type" }, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "input_references", "required": false, "schema": { "items": { "oneOf": [ { "additionalProperties": false, "properties": { "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "type": { "const": "video_url" }, "video_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" } }, "required": [ "type", "video_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "audio_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "audio_url" } }, "required": [ "type", "audio_url" ], "type": "object" } ] }, "type": "array" }, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "callback_url", "pattern": "^https://", "required": false, "schema": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "maxLength": 256, "name": "session_id", "required": false, "schema": { "maxLength": 256, "type": "string" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "schema": { "additionalProperties": true, "properties": { "generation_name": { "type": "string" }, "parent_span_id": { "type": "string" }, "span_name": { "type": "string" }, "trace_id": { "type": "string" }, "trace_name": { "type": "string" } }, "type": "object" }, "type": "object" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "schema": { "maxLength": 256, "type": "string" }, "type": "string" } ], "request_schema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "aspect_ratio": { "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, "callback_url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" }, "creativity": false, "duration": { "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "maximum": 600, "minimum": 1, "type": "integer" }, "frame_images": { "items": { "additionalProperties": false, "properties": { "frame_type": { "enum": [ "first_frame", "last_frame" ] }, "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url", "frame_type" ], "type": "object" }, "maxItems": 2, "minItems": 1, "type": "array", "x-source-unique-role": "frame_type" }, "generate_audio": { "enum": [ false, true ], "x-omitted-default": "published audio capability when true/false; unknown if null; output audio must be measured" }, "input_references": { "items": { "oneOf": [ { "additionalProperties": false, "properties": { "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "type": { "const": "video_url" }, "video_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" } }, "required": [ "type", "video_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "audio_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "audio_url" } }, "required": [ "type", "audio_url" ], "type": "object" } ] }, "type": "array" }, "model": { "const": "minimax/hailuo-3" }, "previous_job_id": false, "prompt": { "minLength": 1, "type": "string", "x-source-max-utf8-bytes": 10000, "x-source-non-whitespace": true }, "provider": false, "resolution": { "enum": [ "2K" ] }, "seed": false, "session_id": { "maxLength": 256, "type": "string" }, "size": false, "trace": { "additionalProperties": true, "properties": { "generation_name": { "type": "string" }, "parent_span_id": { "type": "string" }, "span_name": { "type": "string" }, "trace_id": { "type": "string" }, "trace_name": { "type": "string" } }, "type": "object" }, "upscale_factor": false, "user": { "maxLength": 256, "type": "string" } }, "required": [ "model", "prompt", "duration" ], "title": "Video generation request", "type": "object", "x-source-global-rules": [ "No null values or duplicate keys at any JSON object level", "No duration/resolution/aspect default is inserted", "Prompt required for all21 despite broader official image-only schema", "A request must also pass model membership, exact price card, SKU selection and frozen quote construction", "Non-string known trace fields reject; other trace keys retain arbitrary JSON", "No n/output-count/client price fields accepted", "Provider passthrough disabled for all21; feed allowlist names do not supply provider slug/value contract" ], "x-source-material-combinations": [ "Exact model/card, positive published duration, model resolution/aspect membership and valid frozen quote are all required; independent enum arrays are not proven provider Cartesian combinations.", "Use exact published size or compatible resolution/aspect. Omitted options stay omitted; no guessed geometry.", "first_frame/last_frame roles each occur at most once; frame_images wins mode precedence over input_references.", "provider options are unavailable for this model despite any published passthrough-name allowlist.", "Frame images plus image references are rejected because mixed additive input count is unproved; pure frame or pure reference mode remains separately priced." ] }, "unsupported": [ "size", "seed", "provider", "previous_job_id", "upscale_factor", "creativity" ] }, "input": { "additional_properties": false, "content_type": "application/json", "material_types": [ "text", "image", "audio", "video" ], "optional_controls": [ "resolution", "aspect_ratio", "generate_audio", "frame_images", "input_references", "callback_url", "session_id", "trace", "user" ], "required": [ "model", "prompt", "duration" ] }, "lifecycle": { "cancel_endpoint": null, "content": [ { "http": "GET", "path": "/v1/videos/{public_id}/content", "query": { "index": "actual output index" } } ], "create": { "http": "POST", "path": "/v1/videos" }, "mode": "submit_once_poll_original", "public_id": "video_; owner user/key/group scope", "status": [ { "http": "GET", "path": "/v1/videos/{public_id}" } ], "submit_status": 202, "terminal_failure_public": "200 failed + charge_pending_check=true; inspect original operation", "terminal_provider_states": [ "failed", "cancelled", "expired" ], "unknown": "503 result_pending_check + originalid + X-Should-Retry:false; never replay original" }, "method": { "http": "POST", "path": "/v1/videos" }, "method_aliases": [], "operation_modes": [ "text_to_video", "image_to_video_frame_images", "reference_to_video" ], "output": { "content_range_supported": true, "every_actual_output": true, "family": "video", "fields": [ { "condition": "Always present for each completed output.", "description": "Zero-based position of this video in the outputs list.", "field_path": "outputs[].index", "json_schema": { "type": "integer" }, "name": "index", "nullable": false, "type": "integer" }, { "condition": "Present after the owned result is available and a signed URL is created.", "description": "Signed HTTPS download URL for this completed video.", "field_path": "outputs[].content_url", "json_schema": { "type": "string" }, "name": "content_url", "nullable": false, "type": "string" }, { "condition": "A nonempty recorded digest is returned; otherwise null.", "description": "SHA-256 digest of the original video bytes; null if unavailable.", "field_path": "outputs[].sha256", "json_schema": { "type": [ "string", "null" ] }, "name": "sha256", "nullable": true, "type": "string | null" }, { "condition": "Returned when the recorded file size is positive.", "description": "Size of the original video file in bytes; null if unavailable.", "field_path": "outputs[].size_bytes", "json_schema": { "type": [ "integer", "null" ] }, "name": "size_bytes", "nullable": true, "type": "integer | null" }, { "condition": "Returned when the measured duration is positive.", "description": "Measured video duration in milliseconds; null if unavailable.", "field_path": "outputs[].duration_ms", "json_schema": { "type": [ "integer", "null" ] }, "name": "duration_ms", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video width in pixels; null if unavailable.", "field_path": "outputs[].width", "json_schema": { "type": [ "integer", "null" ] }, "name": "width", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video height in pixels; null if unavailable.", "field_path": "outputs[].height", "json_schema": { "type": [ "integer", "null" ] }, "name": "height", "nullable": true, "type": "integer | null" }, { "condition": "Returned together with positive recorded width and height.", "description": "Video codec identifier; null if not recorded.", "field_path": "outputs[].video_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "video_codec", "nullable": true, "type": "string | null" }, { "condition": "Returned when width, height and the video codec are recorded; false is a known result.", "description": "Whether the video contains an audio track; null if not measured.", "field_path": "outputs[].has_audio", "json_schema": { "type": [ "boolean", "null" ] }, "name": "has_audio", "nullable": true, "type": "boolean | null" }, { "condition": "Returned when video metadata is recorded and the audio codec identifier is nonempty.", "description": "Audio codec identifier; null when no identifier is recorded.", "field_path": "outputs[].audio_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "audio_codec", "nullable": true, "type": "string | null" } ], "format": "original MP4 bytes; no normalization/transcode", "max_aggregate_seconds": 2400, "max_bytes_per_output": 67108864, "max_seconds_per_output": 600, "result": "signed owned content URLs", "unmeasured_fields_nullable": true } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "conditions": "No additional condition is declared in this pricing key.", "quoted_unit": "per video second" }, "label": "Video price", "units": [ { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" } ] }, { "dimensions": { "quoted_unit": "per reference image" }, "label": "reference image", "units": [ { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "examples": [ { "code": "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\",\"prompt\":\"A serene mountain landscape at sunset\",\"resolution\":\"2K\"}', encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('result.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\n", "label": "curl · create video", "language": "bash" }, { "code": "set -eu\n: \"${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 $AILOOT_API_KEY\" -D status-headers.txt -o status.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('status.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\n", "label": "GET original status", "language": "bash" }, { "code": "set -eu\n: \"${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\n", "label": "Save every completed owned output", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "videos", "hints": [], "http": "POST", "in": null, "input": [ "text", "image", "audio", "video" ], "label": "Видео", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "video" ], "path": "/v1/videos", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "conditions": "No additional condition is declared in this pricing key.", "quoted_unit": "per video second" }, "label": "Video price", "units": [ { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" } ] }, { "dimensions": { "quoted_unit": "per reference image" }, "label": "reference image", "units": [ { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "minimax/hailuo-3", "route_label": "Ultra", "status_reads": [ "GET /v1/videos/{public_id}", "GET /v1/videos/{public_id}/content" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" }, { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" }, { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } } ], "model_id": "minimax/hailuo-3", "nativeProvenance": { "input_facts_canonical_sha256": "b7d3bfda55c7a9daf7f3df0865b7ca57e0f33e61d4d7c555e7263a470715acb1", "input_html_sha256": "769930630f98621cd06a3a7e79c3f86b591bb24a1e11178c3ff2e7d731e54a08", "private_audit_sha256": "269a27a6a7b8fb4f62cd14e555a92d89894557769744af07f0d325383dd1558f", "role": "historical-normalized-input-audit-hashes", "schema": "ailoot-native-model-provenance-v2" }, "page": { "canonical": "https://ailoot.ai/models/en/minimax-hailuo-3/", "description": "MiniMax H3 generates short video with native stereo audio from text, frame images or multimodal references. It supports first/last-frame creation, reference-guided editing and motion or voice relationships, with 4–15-second output and a distinct 2K regeneration workflow.", "locale": "en", "md_url": "https://ailoot.ai/models/en/minimax-hailuo-3/index.md", "title": "MiniMax: H3 — Ailoot", "url": "https://ailoot.ai/models/en/minimax-hailuo-3/" }, "rawModel": { "about": "One audiovisual result from a multimodal brief\n\nMiniMax H3 is MiniMax’s omni-modal video system. It interprets text, images, video and audio together, then generates video with native stereo sound. The maker presents it for short creative work such as product visuals, advertising, animated posters and film-title concepts, where the relationships among reference assets matter as much as the scene description.\n\nThe documented system produces 4–15-second video at 24 frames per second with 32 kHz stereo audio. Its H3-Base generation operates at 768p; the full 2K workflow regenerates that result using the original multimodal context. This is more than a conventional resize: the second stage uses the model and source context again to recover fine detail. H3 Max and H3-Context-IR have separate roles and limits.\n\nText and frame-guided creation\n\nText-only input describes the complete audiovisual timeline. A first image anchors the opening, a last image anchors the ending, and two images can define both. For a first-frame shot, begin with the composition and identity visible in the still, then describe the action developing from it. For a first-to-last-frame transition, describe the observable movement connecting the two states rather than repeat two unrelated image descriptions.\n\nA practical product brief can specify a closed package in the opening frame, the hand that opens it, the camera’s gentle movement and the final state to reach. Preserve the object’s shape, label placement and lighting in the supplied frames. Frame-guided creation and reference-guided creation are separate input modes; the maker’s interface does not mix first/last-frame roles with reference-media roles in one request.\n\nReference-guided generation and editing\n\nThe reference mode accepts text with images, video clips and audio clips. Identify what each source contributes: a character’s appearance, a location, camera motion, the temporal structure of a source clip or a voice. A video used only for camera movement is different from a video that should actually be edited or continued. State that relationship explicitly.\n\nThe maker’s reference guide separates subject definitions, a task summary, retention analysis, a detailed shot description, overall soundscape and audience-only background music. It distinguishes preservation of visible content from attribute transfer or a broad style reference. For audio, copying a signal is different from referencing timbre, rhythm or delivery. Keep those roles stable throughout the brief.\n\nFor a reference-driven scene, supply a character image, a short camera-movement reference and an audio voice reference, then describe where each should affect the target shot. State which clothing, environment or object details must remain recognizable. Compare the finished clip with those requirements, including motion continuity and the relationship between the visible speaker and the voice heard.\n\nSpeech, sound and shot timing\n\nH3 jointly models dialogue, physical sounds, ambience and music. The model card documents stable dialogue support for Arabic, Chinese, English, French, German, Italian, Japanese, Korean, Portuguese, Russian and Spanish; other languages are described as varying in support. Provide the exact spoken words and language, with a stable speaker identity across shots.\n\nThe maker’s prompt-writing guides use English for descriptive sections while preserving dialogue and visible text in their original language. Spoken content uses `[Language] ...`, with speaker identity and voice description outside the block. Distinguish physical speech from off-screen voiceover, and identify when a line continues across a cut or is cut off by the end. Preserve visible text exactly as well. Fit the amount of speech to the chosen duration and inspect the rendered words and audible line together.\n\nDescribe camera movement as an action, including its range and speed when they matter. Number shots in playback order and keep cut times within the video duration. Separate scene sounds such as footsteps or a door closing from background score audible only to the audience. These choices make a short shot plan easier to interpret and easier to review against its result.\n\nInput preparation and numerical limits\n\nThe current generation schema requires non-empty text in every mode, with up to 7,000 characters per text item. Images can be JPG, JPEG, PNG, WebP, HEIC or HEIF, up to 30 MB each, with each side from 256 to 5,760 pixels and aspect ratio from 0.4 to 2.5. Frame input permits one opening and one ending image; reference mode permits up to nine reference images.\n\nReference video can contain up to three MP4 or MOV clips, each 2–15 seconds and together no more than 15 seconds. A clip can be up to 50 MB; its video codec is H.264 or H.265, with 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 supports up to three WAV or MP3 clips, up to 15 MB each, each 2–15 seconds and together no more than 15 seconds. The model card caps mixed reference inputs at 12 files. The documented request-body limit is 64 MB, distinct from the per-file limits.\n\nChoose only references that contribute to the brief and make every contribution explicit. A clear subject view is more useful than several conflicting views with no explanation. Preserve reference order, crop away irrelevant material without removing necessary scene context and check that short source clips contain the action or voice characteristic being requested.\n\nOutput shape and the complete system\n\nThe manufacturer’s H3 interface offers 768P and 2K. Text-only generation requires a concrete ratio: 21:9, 16:9, 4:3, 1:1, 3:4 or 9:16. First/last-frame creation takes its aspect ratio from the input image; reference creation can use an adaptive or explicit ratio. Integer output duration is 4–15 seconds.\n\nThe model card distinguishes H3-Context-IR, which interprets and enriches the brief, H3-Base, which generates audiovisual content, and H3-Regenerate-2K, which creates the higher-resolution result. The released base checkpoints separate frame-guided and omni-reference tasks. The context and regeneration components are distinct from those base weights, so the name of an open checkpoint alone does not establish the whole system’s behavior.\n\nThe maker’s generation workflow is asynchronous. Its task-query interface retrieves tasks from the preceding seven days. Keep the task identity until the actual video result is returned, then save the clip rather than retain only a time-limited download address. Review visual identity, small text, object interactions, spoken content and sound timing at the intended viewing size. The manufacturer identifies multimodal understanding and fine visual detail as continuing areas for improvement; a detailed brief and source comparison remain central to a useful result.", "alias_of": null, "aliases": [], "author": "MiniMax", "available": null, "canonical_model": "minimax/hailuo-3", "capabilities": { "context_length": 0, "manufacturer_input": [ "text", "image", "video", "audio" ], "manufacturer_output": [ "video" ] }, "card_routes": [ { "label": "Ultra", "rates": [ { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ], "summary": "Full configuration pricing in details." } ], "ctx": null, "declared_tariff_references": [ { "client_selectable": false, "key": "ffcc346d33bca9e66b22f181", "label": "Video configuration price references", "profiles": [ { "basis": "Published price reference for the configuration shown. Final charges follow the actual billed configuration.", "dimensions": { "conditions": "No additional condition is declared in this pricing key." }, "label": "Video price", "units": [ { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "key": "video_second", "label": "Video price", "public_unit_label": "per video second", "quantity": 1, "rate_role": "typed_video_second_reference", "side": "out", "unit": "video_second" } ] }, { "basis": "The first five reference images are free; the listed per-image rate applies after the first five. Published price reference for the configuration shown. Final charges follow the actual billed configuration.", "dimensions": { "conditions": "No additional condition is declared in this pricing key." }, "label": "Reference images after the first five", "units": [ { "amount": "0.08", "amount_unit": "usd_per_image", "billing_input": false, "key": "input_image", "label": "Reference images after the first five", "public_unit_label": "per image", "quantity": 1, "rate_role": "typed_video_image_reference", "side": "in", "unit": "image" } ] } ] } ], "entity_type": "model", "formats": [ "videos" ], "id": "minimax/hailuo-3", "input": [ "text", "image", "audio", "video" ], "kind": "video", "max_out": null, "methods": [ { "available": null, "billing_basis": { "basis": "original_invoice_usd", "description": "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.", "forecast_quantity_is_estimate": true, "physical_output_is_billable_quantity": false, "version": "original_invoice_usd_v1" }, "cache_read": null, "cache_write": null, "cache_write_1h": null, "contract": { "data": { "all_results": "Keep every actual owned output and its returned measured metadata.", "defaults": { "aspect_ratio": null, "duration": null, "generate_audio": "endpoint capability flag when published; omitted unknown stays unknown; never guarantees audio track", "resolution": null, "seed": null, "size": null, "wire_omissions_preserved": true }, "errors": [ { "condition": "Video access is unavailable, or this video ID was not found.", "http_status": 404, "public_identifier_field": "error.type", "recovery": "Check video access. For an existing video, use its original public ID and the same API key.", "type": "not_found_error" }, { "condition": "The API key does not match the authenticated account.", "http_status": 401, "public_identifier_field": "error.type", "recovery": "Check your API key and account access before submitting.", "type": "authentication_error" }, { "condition": "The request could not be read, or the download index is invalid.", "http_status": 400, "public_identifier_field": "error.type", "recovery": "Correct the request body. For a download, choose an output index returned by the original task.", "type": "invalid_request_error" }, { "condition": "The selected video configuration cannot be priced.", "http_status": 422, "public_identifier_field": "error.type", "recovery": "Choose a supported video configuration and complete its required options before submitting a corrected request.", "type": "price_unavailable" }, { "condition": "A video input or original continuation task is invalid.", "http_status": 422, "public_identifier_field": "error.type", "recovery": "Use valid HTTPS inputs. For continuation, use your completed original public video ID with the same API key.", "type": "invalid_request_error" }, { "condition": "The available balance or limits do not allow a reservation.", "http_status": 402, "public_identifier_field": "error.type", "recovery": "Check your available balance and limits before sending a new request.", "type": "billing_error" }, { "condition": "Video verification, storage or service access is temporarily unavailable.", "http_status": 503, "public_identifier_field": "error.type", "recovery": "Wait for service availability. If you already have a video ID, check that original task instead of creating another generation.", "type": "server_error" }, { "code": "result_pending_check", "condition": "The original video result and charge need checking.", "http_status": 503, "public_identifier_field": "error.code", "recovery": "Keep the returned video ID and check that task. Do not send a replacement generation request while it is being checked.", "type": "server_error" }, { "code": "owned_result_unavailable", "condition": "The existing video download is temporarily unavailable.", "http_status": 503, "public_identifier_field": "error.code", "recovery": "Check the same video task later and download its existing output. A new generation creates a separate operation.", "type": "server_error" }, { "condition": "The video content has not been published.", "http_status": 409, "public_identifier_field": "error.type", "recovery": "Check the original task status. Download after it reports completed; if it reports failed, follow its charge-check notice.", "type": "video_not_ready" } ], "hints": [ "No null values or duplicate keys at any JSON object level", "No duration/resolution/aspect default is inserted", "Prompt required for all21 despite broader official image-only schema", "A request must also pass model membership, exact price card, SKU selection and frozen quote construction", "Non-string known trace fields reject; other trace keys retain arbitrary JSON", "No n/output-count/client price fields accepted", "Provider passthrough disabled for all21; feed allowlist names do not supply provider slug/value contract" ], "ignored_fields": [], "lifecycle": { "cancel_endpoint": null, "content": [ { "http": "GET", "path": "/v1/videos/{public_id}/content", "query": { "index": "actual output index" } } ], "create": { "http": "POST", "path": "/v1/videos" }, "mode": "submit_once_poll_original", "public_id": "video_; owner user/key/group scope", "status": [ { "http": "GET", "path": "/v1/videos/{public_id}" } ], "submit_status": 202, "terminal_failure_public": "200 failed + charge_pending_check=true; inspect original operation", "terminal_provider_states": [ "failed", "cancelled", "expired" ], "unknown": "503 result_pending_check + originalid + X-Should-Retry:false; never replay original" }, "material_combinations": [ { "mode": "text_to_video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "Provide prompt as text and duration as whole seconds. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration" ], "required_material": "A written prompt." }, { "exact_keys": [ "type", "image_url", "frame_type" ], "mode": "image_to_video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "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. Use frame images or image references in one request; do not combine both. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration", "frame_images" ], "required_material": "A written prompt and a first-frame image." }, { "mode": "Reference to video", "model": { "enum": [ "minimax/hailuo-3" ], "enum_known": true, "type": "string" }, "prompt": { "max_utf8_bytes": 10000, "non_whitespace": true, "type": "string" }, "representation": "input_references is an array of objects. Set type to image_url, video_url, audio_url, and use the matching field containing url. Use public HTTPS URLs. Omit frame_images to select reference mode. The estimate includes the displayed per-image component only for image references after the first five. Final charge follows the actual billed configuration. Do not combine image references with frame images. Choose a supported resolution and, if needed, an aspect ratio.", "required": [ "model", "prompt", "duration", "input_references" ], "required_material": "A written prompt and supported image, video, audio references." } ], "operation_modes": [ "text_to_video", "image_to_video_frame_images", "reference_to_video" ], "outputs": { "content_range_supported": true, "every_actual_output": true, "family": "video", "fields": [ { "condition": "Always present for each completed output.", "description": "Zero-based position of this video in the outputs list.", "field_path": "outputs[].index", "json_schema": { "type": "integer" }, "name": "index", "nullable": false, "type": "integer" }, { "condition": "Present after the owned result is available and a signed URL is created.", "description": "Signed HTTPS download URL for this completed video.", "field_path": "outputs[].content_url", "json_schema": { "type": "string" }, "name": "content_url", "nullable": false, "type": "string" }, { "condition": "A nonempty recorded digest is returned; otherwise null.", "description": "SHA-256 digest of the original video bytes; null if unavailable.", "field_path": "outputs[].sha256", "json_schema": { "type": [ "string", "null" ] }, "name": "sha256", "nullable": true, "type": "string | null" }, { "condition": "Returned when the recorded file size is positive.", "description": "Size of the original video file in bytes; null if unavailable.", "field_path": "outputs[].size_bytes", "json_schema": { "type": [ "integer", "null" ] }, "name": "size_bytes", "nullable": true, "type": "integer | null" }, { "condition": "Returned when the measured duration is positive.", "description": "Measured video duration in milliseconds; null if unavailable.", "field_path": "outputs[].duration_ms", "json_schema": { "type": [ "integer", "null" ] }, "name": "duration_ms", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video width in pixels; null if unavailable.", "field_path": "outputs[].width", "json_schema": { "type": [ "integer", "null" ] }, "name": "width", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video height in pixels; null if unavailable.", "field_path": "outputs[].height", "json_schema": { "type": [ "integer", "null" ] }, "name": "height", "nullable": true, "type": "integer | null" }, { "condition": "Returned together with positive recorded width and height.", "description": "Video codec identifier; null if not recorded.", "field_path": "outputs[].video_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "video_codec", "nullable": true, "type": "string | null" }, { "condition": "Returned when width, height and the video codec are recorded; false is a known result.", "description": "Whether the video contains an audio track; null if not measured.", "field_path": "outputs[].has_audio", "json_schema": { "type": [ "boolean", "null" ] }, "name": "has_audio", "nullable": true, "type": "boolean | null" }, { "condition": "Returned when video metadata is recorded and the audio codec identifier is nonempty.", "description": "Audio codec identifier; null when no identifier is recorded.", "field_path": "outputs[].audio_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "audio_codec", "nullable": true, "type": "string | null" } ], "format": "original MP4 bytes; no normalization/transcode", "max_aggregate_seconds": 2400, "max_bytes_per_output": 67108864, "max_seconds_per_output": 600, "result": "signed owned content URLs", "unmeasured_fields_nullable": true }, "parameters": [ { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "minimax/hailuo-3" ], "enum_known": true, "name": "model", "required": true, "schema": { "const": "minimax/hailuo-3" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "minLength": 1, "name": "prompt", "required": true, "schema": { "minLength": 1, "type": "string", "x-source-max-utf8-bytes": 10000, "x-source-non-whitespace": true }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "enum_known": true, "maximum": 600, "minimum": 1, "name": "duration", "required": true, "schema": { "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "maximum": 600, "minimum": 1, "type": "integer" }, "type": "integer" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "2K" ], "enum_known": true, "name": "resolution", "required": false, "schema": { "enum": [ "2K" ] }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ], "enum_known": true, "name": "aspect_ratio", "required": false, "schema": { "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": [ false, true ], "enum_known": true, "name": "generate_audio", "required": false, "schema": { "enum": [ false, true ], "x-omitted-default": "published audio capability when true/false; unknown if null; output audio must be measured" }, "type": "boolean" }, { "availability": "source_interface", "conditions": "These keys describe each frame object; image_url contains only url. Omit frame_images for a text-only request.", "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.", "default": null, "default_known": false, "enum": null, "enum_known": false, "exact_keys": [ "type", "image_url", "frame_type" ], "maxItems": 2, "max_items": 2, "minItems": 1, "min_items": 1, "name": "frame_images", "required": false, "schema": { "items": { "additionalProperties": false, "properties": { "frame_type": { "enum": [ "first_frame", "last_frame" ] }, "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url", "frame_type" ], "type": "object" }, "maxItems": 2, "minItems": 1, "type": "array", "x-source-unique-role": "frame_type" }, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "input_references", "required": false, "schema": { "items": { "oneOf": [ { "additionalProperties": false, "properties": { "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "type": { "const": "video_url" }, "video_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" } }, "required": [ "type", "video_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "audio_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "audio_url" } }, "required": [ "type", "audio_url" ], "type": "object" } ] }, "type": "array" }, "type": "array" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "callback_url", "pattern": "^https://", "required": false, "schema": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "maxLength": 256, "name": "session_id", "required": false, "schema": { "maxLength": 256, "type": "string" }, "type": "string" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "name": "trace", "required": false, "schema": { "additionalProperties": true, "properties": { "generation_name": { "type": "string" }, "parent_span_id": { "type": "string" }, "span_name": { "type": "string" }, "trace_id": { "type": "string" }, "trace_name": { "type": "string" } }, "type": "object" }, "type": "object" }, { "availability": "source_interface", "default": null, "default_known": false, "enum": null, "enum_known": false, "maxLength": 256, "name": "user", "required": false, "schema": { "maxLength": 256, "type": "string" }, "type": "string" } ], "request_schema": { "$schema": "https://json-schema.org/draft/2020-12/schema", "additionalProperties": false, "properties": { "aspect_ratio": { "enum": [ "21:9", "16:9", "4:3", "1:1", "3:4", "9:16" ] }, "callback_url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" }, "creativity": false, "duration": { "enum": [ 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15 ], "maximum": 600, "minimum": 1, "type": "integer" }, "frame_images": { "items": { "additionalProperties": false, "properties": { "frame_type": { "enum": [ "first_frame", "last_frame" ] }, "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url", "frame_type" ], "type": "object" }, "maxItems": 2, "minItems": 1, "type": "array", "x-source-unique-role": "frame_type" }, "generate_audio": { "enum": [ false, true ], "x-omitted-default": "published audio capability when true/false; unknown if null; output audio must be measured" }, "input_references": { "items": { "oneOf": [ { "additionalProperties": false, "properties": { "image_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "image_url" } }, "required": [ "type", "image_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "type": { "const": "video_url" }, "video_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" } }, "required": [ "type", "video_url" ], "type": "object" }, { "additionalProperties": false, "properties": { "audio_url": { "additionalProperties": false, "properties": { "url": { "format": "uri", "pattern": "^https://", "type": "string", "x-source-rule": "public HTTPS; no userinfo, fragment, whitespace, private/reserved hosts; own-media links additionally require owner/signature/status/hash/MIME/bytes" } }, "required": [ "url" ], "type": "object" }, "type": { "const": "audio_url" } }, "required": [ "type", "audio_url" ], "type": "object" } ] }, "type": "array" }, "model": { "const": "minimax/hailuo-3" }, "previous_job_id": false, "prompt": { "minLength": 1, "type": "string", "x-source-max-utf8-bytes": 10000, "x-source-non-whitespace": true }, "provider": false, "resolution": { "enum": [ "2K" ] }, "seed": false, "session_id": { "maxLength": 256, "type": "string" }, "size": false, "trace": { "additionalProperties": true, "properties": { "generation_name": { "type": "string" }, "parent_span_id": { "type": "string" }, "span_name": { "type": "string" }, "trace_id": { "type": "string" }, "trace_name": { "type": "string" } }, "type": "object" }, "upscale_factor": false, "user": { "maxLength": 256, "type": "string" } }, "required": [ "model", "prompt", "duration" ], "title": "Video generation request", "type": "object", "x-source-global-rules": [ "No null values or duplicate keys at any JSON object level", "No duration/resolution/aspect default is inserted", "Prompt required for all21 despite broader official image-only schema", "A request must also pass model membership, exact price card, SKU selection and frozen quote construction", "Non-string known trace fields reject; other trace keys retain arbitrary JSON", "No n/output-count/client price fields accepted", "Provider passthrough disabled for all21; feed allowlist names do not supply provider slug/value contract" ], "x-source-material-combinations": [ "Exact model/card, positive published duration, model resolution/aspect membership and valid frozen quote are all required; independent enum arrays are not proven provider Cartesian combinations.", "Use exact published size or compatible resolution/aspect. Omitted options stay omitted; no guessed geometry.", "first_frame/last_frame roles each occur at most once; frame_images wins mode precedence over input_references.", "provider options are unavailable for this model despite any published passthrough-name allowlist.", "Frame images plus image references are rejected because mixed additive input count is unproved; pure frame or pure reference mode remains separately priced." ] }, "unsupported": [ "size", "seed", "provider", "previous_job_id", "upscale_factor", "creativity" ] }, "input": { "additional_properties": false, "content_type": "application/json", "material_types": [ "text", "image", "audio", "video" ], "optional_controls": [ "resolution", "aspect_ratio", "generate_audio", "frame_images", "input_references", "callback_url", "session_id", "trace", "user" ], "required": [ "model", "prompt", "duration" ] }, "lifecycle": { "cancel_endpoint": null, "content": [ { "http": "GET", "path": "/v1/videos/{public_id}/content", "query": { "index": "actual output index" } } ], "create": { "http": "POST", "path": "/v1/videos" }, "mode": "submit_once_poll_original", "public_id": "video_; owner user/key/group scope", "status": [ { "http": "GET", "path": "/v1/videos/{public_id}" } ], "submit_status": 202, "terminal_failure_public": "200 failed + charge_pending_check=true; inspect original operation", "terminal_provider_states": [ "failed", "cancelled", "expired" ], "unknown": "503 result_pending_check + originalid + X-Should-Retry:false; never replay original" }, "method": { "http": "POST", "path": "/v1/videos" }, "method_aliases": [], "operation_modes": [ "text_to_video", "image_to_video_frame_images", "reference_to_video" ], "output": { "content_range_supported": true, "every_actual_output": true, "family": "video", "fields": [ { "condition": "Always present for each completed output.", "description": "Zero-based position of this video in the outputs list.", "field_path": "outputs[].index", "json_schema": { "type": "integer" }, "name": "index", "nullable": false, "type": "integer" }, { "condition": "Present after the owned result is available and a signed URL is created.", "description": "Signed HTTPS download URL for this completed video.", "field_path": "outputs[].content_url", "json_schema": { "type": "string" }, "name": "content_url", "nullable": false, "type": "string" }, { "condition": "A nonempty recorded digest is returned; otherwise null.", "description": "SHA-256 digest of the original video bytes; null if unavailable.", "field_path": "outputs[].sha256", "json_schema": { "type": [ "string", "null" ] }, "name": "sha256", "nullable": true, "type": "string | null" }, { "condition": "Returned when the recorded file size is positive.", "description": "Size of the original video file in bytes; null if unavailable.", "field_path": "outputs[].size_bytes", "json_schema": { "type": [ "integer", "null" ] }, "name": "size_bytes", "nullable": true, "type": "integer | null" }, { "condition": "Returned when the measured duration is positive.", "description": "Measured video duration in milliseconds; null if unavailable.", "field_path": "outputs[].duration_ms", "json_schema": { "type": [ "integer", "null" ] }, "name": "duration_ms", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video width in pixels; null if unavailable.", "field_path": "outputs[].width", "json_schema": { "type": [ "integer", "null" ] }, "name": "width", "nullable": true, "type": "integer | null" }, { "condition": "Width, height and the video codec are returned together when recorded.", "description": "Video height in pixels; null if unavailable.", "field_path": "outputs[].height", "json_schema": { "type": [ "integer", "null" ] }, "name": "height", "nullable": true, "type": "integer | null" }, { "condition": "Returned together with positive recorded width and height.", "description": "Video codec identifier; null if not recorded.", "field_path": "outputs[].video_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "video_codec", "nullable": true, "type": "string | null" }, { "condition": "Returned when width, height and the video codec are recorded; false is a known result.", "description": "Whether the video contains an audio track; null if not measured.", "field_path": "outputs[].has_audio", "json_schema": { "type": [ "boolean", "null" ] }, "name": "has_audio", "nullable": true, "type": "boolean | null" }, { "condition": "Returned when video metadata is recorded and the audio codec identifier is nonempty.", "description": "Audio codec identifier; null when no identifier is recorded.", "field_path": "outputs[].audio_codec", "json_schema": { "type": [ "string", "null" ] }, "name": "audio_codec", "nullable": true, "type": "string | null" } ], "format": "original MP4 bytes; no normalization/transcode", "max_aggregate_seconds": 2400, "max_bytes_per_output": 67108864, "max_seconds_per_output": 600, "result": "signed owned content URLs", "unmeasured_fields_nullable": true } }, "ctx": null, "declared_pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "conditions": "No additional condition is declared in this pricing key.", "quoted_unit": "per video second" }, "label": "Video price", "units": [ { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" } ] }, { "dimensions": { "quoted_unit": "per reference image" }, "label": "reference image", "units": [ { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "examples": [ { "code": "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\",\"prompt\":\"A serene mountain landscape at sunset\",\"resolution\":\"2K\"}', encoding='utf-8')\nPY_REQUEST\ncurl --fail-with-body --silent --show-error https://api.ailoot.ai/v1/videos \\\n -H \"Authorization: Bearer $AILOOT_API_KEY\" -H 'Content-Type: application/json' \\\n --data-binary @request.json -D response-headers.txt -o result.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('result.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\n", "label": "curl · create video", "language": "bash" }, { "code": "set -eu\n: \"${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 $AILOOT_API_KEY\" -D status-headers.txt -o status.json\npython3 - <<'PY_RESULT'\nimport json\nfrom pathlib import Path\nr=json.loads(Path('status.json').read_text())\nprint(json.dumps(r,ensure_ascii=False,indent=2))\nprint('Keep the complete JSON and response headers; do not resubmit an unknown creation.')\nPY_RESULT\n", "label": "GET original status", "language": "bash" }, { "code": "set -eu\n: \"${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\n", "label": "Save every completed owned output", "language": "bash" } ], "family": "openai", "fast_multiplier": null, "flex_multiplier": null, "fmt": "videos", "hints": [], "http": "POST", "in": null, "input": [ "text", "image", "audio", "video" ], "label": "Видео", "max_out": null, "max_reasoning_effort_multiplier": null, "method_aliases": [], "out": null, "output": [ "video" ], "path": "/v1/videos", "price_conditions": [ { "label": "Fast mode", "value": "Not specified", "when": "When fast mode is selected" }, { "label": "Flex mode", "value": "Not specified", "when": "When flex mode is selected" }, { "label": "Maximum reasoning effort", "value": "Not specified", "when": "When maximum reasoning effort uses the default adjustment" } ], "pricing": { "billing_mode": "original_invoice_usd", "image_input_price": null, "image_output_price": null }, "pricing_profiles": [ { "dimensions": { "regime": "base" }, "label": "Base token rates", "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" } ] }, { "dimensions": { "conditions": "No additional condition is declared in this pricing key.", "quoted_unit": "per video second" }, "label": "Video price", "units": [ { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" } ] }, { "dimensions": { "quoted_unit": "per reference image" }, "label": "reference image", "units": [ { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" } ] }, { "basis": "This estimate is not an additional charge or a fixed rate for the completed generation.", "dimensions": { "forecast_quantity": "one generation estimate" }, "label": "Estimated generation cost", "units": [ { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "request_model_id": "minimax/hailuo-3", "route_label": "Ultra", "status_reads": [ "GET /v1/videos/{public_id}", "GET /v1/videos/{public_id}/content" ], "tiers": [], "units": [ { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "input_price", "label": "Input tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "output_price", "label": "Output tokens", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "output_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "output_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_read_price", "label": "Cache read", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "cached_input_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "cached_input_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_price", "label": "Cache write", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "generic_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "generic_cache_creation_token" }, { "amount": null, "amount_unit": "usd_per_thousand_tokens", "billing_input": false, "estimate_only": true, "key": "cache_write_1h_price", "label": "Cache write, 1 hour", "native_amount_usd_per_unit": null, "native_quantity": 1, "native_unit": "one_hour_cache_creation_token", "public_unit_label": "/ 1K tokens", "quantity": 1000, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "one_hour_cache_creation_token" }, { "amount": "0.26", "amount_unit": "usd_per_video_second", "billing_input": false, "estimate_only": true, "key": "duration_seconds", "label": "Video price", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "public_unit_label": "per video second", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "video_second" }, { "amount": "0.08", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "public_unit_label": "per reference image", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "in", "unit": "reference_images" }, { "amount": "1.3", "amount_unit": "usd_per_exact_native_unit", "billing_input": false, "estimate_only": true, "key": "forecast_usd", "label": "Estimated generation cost", "native_amount_usd_per_unit": "1.3", "native_quantity": 1, "public_unit_label": "estimate before generation", "quantity": 1, "quantity_is_estimate": true, "rate_role": "typed_native_retail_rate", "side": "out", "unit": "request_estimate" } ] } ], "model_aliases": [ { "canonical_model_id": "minimax/hailuo-3", "request_model_id": "minimax/hailuo-3", "route_label": "Ultra" } ], "name": "MiniMax: H3", "price": { "estimate_only": true, "in": null, "in_label": null, "out": 1.3, "out_label": "estimate before generation", "scope_label": "Estimated generation cost", "sort_in": null, "sort_out": 1.3, "varies": false }, "pricing_profiles": [ { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "input_materials_additive": true, "resolution": "768P" }, "label": "Ultra", "units": [ { "amount": "0.16", "amount_unit": "usd_per_output_video_second", "conditions": { "input_materials_additive": true, "resolution": "768P" }, "key": "base", "label": "base", "profile_index": 0, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "output_video_second" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "input_materials_additive": true, "resolution": "2K" }, "label": "Ultra", "units": [ { "amount": "0.26", "amount_unit": "usd_per_output_video_second", "conditions": { "input_materials_additive": true, "resolution": "2K" }, "key": "base", "label": "base", "profile_index": 1, "quantity": "1", "rate_role": "binding_component_rate", "side": "out", "unit": "output_video_second" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_output": true, "output_resolution": "768P" }, "label": "Ultra", "units": [ { "amount": "0.16", "amount_unit": "usd_per_input_video_second", "conditions": { "adds_to_output": true, "output_resolution": "768P" }, "key": "input_video", "label": "input video", "profile_index": 2, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "input_video_second" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_output": true, "output_resolution": "2K" }, "label": "Ultra", "units": [ { "amount": "0.26", "amount_unit": "usd_per_input_video_second", "conditions": { "adds_to_output": true, "output_resolution": "2K" }, "key": "input_video", "label": "input video", "profile_index": 3, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "input_video_second" } ] }, { "applicability": { "client_selectable": false, "native_profile_selection_pending": true, "scope": "manufacturer_reference" }, "dimensions": { "adds_to_output": true, "first_free_reference_images": 5, "only_additional_images_charged": true, "reference_audio_free": true }, "label": "Ultra", "units": [ { "amount": "0.08", "amount_unit": "usd_per_input_image", "conditions": { "adds_to_output": true, "first_free_reference_images": 5, "only_additional_images_charged": true, "reference_audio_free": true }, "key": "input_image", "label": "input image", "profile_index": 4, "quantity": "1", "rate_role": "binding_component_rate", "side": "in", "unit": "input_image" } ] }, { "applicability": { "client_selectable": false, "no_method_admission_claim": true, "scope": "supplier_tariff_reference" }, "dimensions": {}, "label": "Ailoot Ultra · Tariff components", "units": [ { "amount": "0.26", "amount_unit": "usd_per_exact_physical_unit", "basis": "output second", "billing_original_currency": "USD", "billing_original_rate": "0.26", "key": "duration_seconds", "label": "output second", "native_amount_usd_per_unit": "0.26", "native_quantity": 1, "quantity": 1, "side": "out", "unit": "output_second" }, { "amount": "0.08", "amount_unit": "usd_per_exact_physical_unit", "basis": "reference image", "billing_original_currency": "USD", "billing_original_rate": "0.08", "key": "reference_images", "label": "reference image", "native_amount_usd_per_unit": "0.08", "native_quantity": 1, "quantity": 1, "side": "in", "unit": "reference_image" } ] } ], "public_id": "minimax/hailuo-3", "short": "MiniMax H3 generates short video with native stereo audio from text, frame images or multimodal references. It supports first/last-frame creation, reference-guided editing and motion or voice relationships, with 4–15-second output and a distinct 2K regeneration workflow." }, "renderer_schema": { "method_order": "Original DTO methods order; every exact route/format/path/caller survives.", "prices": "Original public DTO fields and original native display HTML; no flattened or normalized offers." }, "representation": "exact-public-dto-and-native-renderer-html", "representationNotes": { "current_reference": { "about_json_pointer": "/aboutHtml", "methods": [ { "contract_json_pointer": "/methods/0/rawMethod/contract", "html_json_pointer": "/methods/0/html", "method_ordinal": 0 } ], "role": "current-semantic-reference" }, "raw_input": { "examples_role": "historical-input-not-current-ready-examples", "json_pointers": [ "/rawModel", "/methods/0/rawMethod" ], "role": "historical-owner-input" }, "schema": "ailoot-native-model-representations-v1" }, "schema": "ailoot-static-model-facts-v1", "schema_version": 1, "shortText": "MiniMax H3 generates short video with native stereo audio from text, frame images or multimodal references. It supports first/last-frame creation, reference-guided editing and motion or voice relationships, with 4–15-second output and a distinct 2K regeneration workflow.", "source": { "audit_sha256": "2e00086bcbfc28e64d0cebe97aa47c17d8d5618963027f8ffb9dc6123d7d25b1", "bridge_map_sha256": "1125275768b9636fc8461bc7da5061239a81ddfe508e2557843ca42c58ab0036", "raw_model_json_sha256": "a74ae193722a08f9dcc5c2f68c2c66990f85ad825f39573a5ab761600883dd90", "renderer_sha256": "fed50305bd3bcc4980ac14df23640efb8c1bc1e819f9d53643d6f43e8974d3fe" }, "sourceRevision": "a0f7567f739deaa3042ffb70a205f62d03d937da4e4824227b7207e3f675c596" }