MiniMaxVideo model확인 중
MiniMax H3 API
minimax-h3-multimodal-reference-to-videoMiniMax H3 video generation with text, image, multimodal reference and regeneration variants.
- Image to video
- Text to video
- Video to video
- Reference to video
- Up to 9 input images
- Up to 15 seconds
- 480p or 768p output
플레이그라운드에서 MiniMax H3 실행
The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.
매개변수
modelMiniMax H3Multimodal reference to videominimax-h3-multimodal-reference-to-video
고급 (1)
input.aigcWatermarkWhether to add an AIGC watermark to the generated video.
작업이 접수되면 크레딧이 예약되고 성공한 경우에만 차감됩니다. 실패한 작업은 예약이 해제되고, 결과가 확인되지 않은 작업은 확인될 때까지 예약이 유지됩니다.
요청 미리보기
{"model": "minimax-h3-multimodal-reference-to-video","input": {"resolution": "768P","duration": "5","ratio": "adaptive","aigcWatermark": false}}웹 Playground는 로그인된 세션으로 이 본문을 보냅니다. 코드에서는 같은 본문을 API 키와 함께 보내세요.
결과
Run the request and the result appears here, with its status and cost.
MiniMax H3 가격
Prices are shown in USD for each available variant and specification. The billing unit is shown with its rate; an official reference appears only when a matching list price is published.
- Charged only on successOnly successful tasks are charged. Failed tasks release reserved credits; tasks with an unconfirmed outcome keep their reservation until the result is verified.
- Safe retries같은 키로 멱등 재시도해도 중복 청구되지 않습니다.
- Price changesexpectedPriceMicros를 보내면 표시 후 가격이 바뀐 경우 PRICE_CHANGED로 작업을 거부합니다.
MiniMax H3 변형 비교
Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.
minimax-h3-max-turbo-image-to-videoImage to video; 텍스트, 이미지; 5–15 s; 480p, 768p
minimax-h3-max-turbo-text-to-videoText to video; 텍스트; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
aspectRatiominimax-h3-max-image-to-videoImage to video; 텍스트, 이미지; 5–15 s; 480p, 768p
minimax-h3-max-text-to-videoText to video; 텍스트; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
ratiominimax-h3-image-to-videoImage to video; 텍스트, 이미지; 5–15 s; 2K, 768p
aigc_watermarkminimax-h3-text-to-videoText to video; 텍스트; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
ratioaigc_watermarkminimax-h3-regeneration-text-to-videoVideo to video; 텍스트, 동영상; 2K
minimax-h3-regeneration-image-to-videoVideo to video; 텍스트, 이미지, 동영상; 2K
firstFrameUrllastFrameUrlminimax-h3-multimodal-reference-to-videoReference to video; 텍스트, 이미지, 동영상, audio; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16
| Variant | 작업 | 입력 | Duration | Resolution | Aspect ratios | Extra fields |
|---|---|---|---|---|---|---|
Max turbo image to videominimax-h3-max-turbo-image-to-video | Image to video | 텍스트, 이미지 | 5–15 s | 480p, 768p | — | — |
Max turbo text to video기본값minimax-h3-max-turbo-text-to-video | Text to video | 텍스트 | 5–15 s | 480p, 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | aspectRatio |
Max image to videominimax-h3-max-image-to-video | Image to video | 텍스트, 이미지 | 5–15 s | 480p, 768p | — | — |
Max text to videominimax-h3-max-text-to-video | Text to video | 텍스트 | 5–15 s | 480p, 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | ratio |
Image to videominimax-h3-image-to-video | Image to video | 텍스트, 이미지 | 5–15 s | 2K, 768p | — | aigc_watermark |
Text to videominimax-h3-text-to-video | Text to video | 텍스트 | 5–15 s | 2K, 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | ratioaigc_watermark |
Regeneration text to videominimax-h3-regeneration-text-to-video | Video to video | 텍스트, 동영상 | — | 2K | — | — |
Regeneration image to videominimax-h3-regeneration-image-to-video | Video to video | 텍스트, 이미지, 동영상 | — | 2K | — | firstFrameUrllastFrameUrl |
Multimodal reference to videominimax-h3-multimodal-reference-to-video | Reference to video | 텍스트, 이미지, 동영상, audio | 5–15 s | 2K, 768p | 21:9, 16:9, 4:3, 1:1, 3:4, 9:16 | — |
MiniMax H3로 할 수 있는 일
MiniMax describes H3 as a multimodal video model that can use text, images, video and audio and generate video with native stereo sound. MiniMax's model documentation describes up to 2K and 15 seconds; actual options depend on the Hermes variant.
The Hermes catalog separates H3, Max and Max Turbo text-to-video and image-to-video, multimodal reference-to-video, and regeneration tasks. The multimodal reference schema lists up to nine images, three videos and three audio inputs. Regeneration variants take a base video; the other variants use different fields. Check the selected variant's status, valid options and price before running.
기능
Up to 15 seconds
Choose a length from 5 to 15 seconds.
durationEvery variant except Regeneration text to video, Regeneration image to video
Start and end frames
Set the first frame and, optionally, the last frame the clip moves to.
firstFrameUrllastFrameUrl변형: Max turbo image to video, Max image to video, Image to video, Regeneration image to video
480p or 768p output
Pick the output resolution: 480p or 768p.
resolutionEvery variant except Regeneration text to video, Regeneration image to video
6 aspect ratios
21:9, 16:9, 4:3, 1:1, 3:4 or 9:16.
aspectRatioratio변형: Max turbo text to video, Max text to video, Text to video, Multimodal reference to video
Up to 9 input images
Send up to 9 images in one request as HTTPS URLs or uploaded media references.
imageUrls변형: Multimodal reference to video
Video input
Accepts a source video as input.
baseVideoUrlvideoUrls변형: Regeneration text to video, Regeneration image to video, Multimodal reference to video
Audio input
Accepts reference audio as input.
audioUrls변형: Multimodal reference to video
활용 사례
Generate a scene
Describe the visual action and sound for a text-to-video task.
Create from references
Use the multimodal variant to supply supported reference media.
Regenerate a clip
Select a regeneration variant when you have a base video and follow its input requirements.
코드에서 MiniMax H3 호출
Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.
- 1
API 키 생성
In the dashboard, with the jobs:create and jobs:read scopes. API 키 - 2
작업 제출
POST /api/v1/jobswith the model ID and an input object. The response is 202 with a task ID. - 3
Poll for the result
GET /api/v1/jobs/{id}until the status is succeeded, then download the output URLs.
최소 요청
Required fields only, generated from the schema of Multimodal reference to video. Set HERMES_API_KEY in your environment.
- Model ID
minimax-h3-multimodal-reference-to-video- 엔드포인트
https://api.hermes-ai.net/api/v1/jobs
# 1. Submit the task (asynchronous; returns 202 with a task id)
curl -X POST https://api.hermes-ai.net/api/v1/jobs \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "minimax-h3-multimodal-reference-to-video",
"input": {
"prompt": "A lighthouse on a rocky coast at sunrise, soft light",
"resolution": "768P",
"duration": "5",
"imageUrls": [
"https://example.com/reference.png"
]
}
}'
# 2. Poll until status is succeeded, failed or reconciliation_required
curl https://api.hermes-ai.net/api/v1/jobs/TASK_ID \
-H "Authorization: Bearer $HERMES_API_KEY"입력 매개변수
Fields of Multimodal reference to video (minimax-h3-multimodal-reference-to-video). 알 수 없는 필드는 INVALID_MODEL_INPUT으로 거부됩니다.
| 필드 | 유형 | 필수 | 기본값 | 허용 값 및 제약 조건 |
|---|---|---|---|---|
prompt | string | 필수 | — | Text prompt for video generation. 1–20480 chars |
imageUrls | string[] | 선택 | — | reference images (max 9) ≤ 9 items, HTTPS image URL or media:<uuid> |
videoUrls | string[] | 선택 | — | reference video ≤ 3 items, HTTPS video URL or media:<uuid> |
audioUrls | string[] | 선택 | — | reference audio ≤ 3 items, HTTPS audio URL or media:<uuid> |
resolution | string | 필수 | "768P" | Output resolution. 허용 값: |
duration | string | 필수 | "5" | Duration in seconds, 5-15. 허용 값: |
ratio | string | 선택 | "adaptive" | Aspect ratio, default adaptive. 허용 값: |
aigcWatermark | boolean | 선택 | — | Whether to add an AIGC watermark to the generated video. |
먼저 로컬 파일 업로드
예시 URL을 반환된 미디어 참조로 바꾸세요.
curl -X POST https://api.hermes-ai.net/api/v1/media \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: image/png" \
--data-binary @input.png
# → { "reference": "media:<uuid>", ... } Use the reference in an image, video or audio field.Headers, response, task statuses and errors
| 헤더 | 값 | 참고 |
|---|---|---|
Authorization | Bearer <API key> | 또는 x-api-key로 키를 보냅니다. |
Content-Type | application/json | |
Idempotency-Key | <unique string ≤128> | 필수입니다. 동일한 요청을 재시도할 때만 재사용하세요. |
| 필드 | 유형 | 참고 |
|---|---|---|
id | string | Hermes AI 작업 ID입니다. 폴링에 사용하세요. |
model | string | 모델 slug입니다. |
status | string | 작업 상태를 참조하세요. |
errorCode | string | null | 작업이 실패하거나 검토가 필요할 때 설정됩니다. |
priceMicros | integer | 접수 시 확정된 견적(USD 마이크로 단위)입니다. |
currency | "USD" | |
createdAt / updatedAt | string | ISO 8601 타임스탬프입니다. |
assets[] | array | { id, type, url?, text? }. url은 동일 출처의 /api/v1/results/<uuid> 링크입니다. |
replayed | boolean | 제출 시에만 해당합니다. 멱등 재시도가 일치하면 true입니다. |
| 상태 | 최종 상태 | 의미 |
|---|---|---|
queued | 아니요 | 접수되어 워커를 기다리는 중입니다. |
submitting | 아니요 | 모델 제공업체로 전송 중입니다. |
running | 아니요 | 모델이 생성 중입니다. |
succeeded | 예 | 완료되었습니다. 결과는 assets에 있습니다. |
failed | 예 | 결과 없이 종료되었습니다. 예약이 해제됩니다. |
reconciliation_required | 예 | The result is being verified. Keep the task ID and do not resubmit automatically. |
| HTTP | 코드 | 의미 및 조치 |
|---|---|---|
401 | AUTH_REQUIRED | API 키 또는 세션이 없거나 유효하지 않습니다. |
403 | INSUFFICIENT_SCOPE | API 키에 이 엔드포인트에 필요한 권한이 없습니다. |
403 | PERMISSION_DENIED | 이 자격 증명으로는 이 작업을 수행할 수 없습니다. |
429 | API_KEY_RATE_LIMITED | API 키의 요청 한도에 도달했습니다. Retry-After를 따르세요. |
429 | API_KEY_USAGE_EXCEEDED | API 키가 사용 한도에 도달했습니다. 새 키를 생성하세요. |
400 | INVALID_REQUEST | 본문이 JSON 객체가 아니거나 필수 값이 없습니다. |
400 | INVALID_IDEMPOTENCY_KEY | Idempotency-Key는 1~128자의 출력 가능한 ASCII 문자여야 합니다. |
400 | INVALID_MODEL_INPUT | input이 모델 스키마와 일치하지 않습니다(알 수 없는 필드, 누락된 필수 필드 또는 잘못된 값). |
400 / 413 | INPUT_TOO_LARGE | 요청 본문이 256KB를 초과합니다. 미디어를 먼저 업로드하고 미디어 참조를 보내세요. |
404 | REQUEST_NOT_FOUND | No chat request with this ID belongs to your account. |
404 | MODEL_NOT_FOUND | 이 slug를 가진 모델이 없습니다. |
404 | JOB_NOT_FOUND | 이 ID의 작업은 계정에 속하지 않습니다. |
409 | IDEMPOTENCY_CONFLICT | 이 Idempotency-Key는 다른 입력으로 사용되었습니다. 새 요청에는 새 키를 사용하세요. |
409 | PRICE_CHANGED | 가격이 expectedPriceMicros와 다릅니다. 가격을 다시 가져와 확인하세요. |
409 | MODEL_PRICE_UNAVAILABLE | 이 모델에는 아직 가격이 설정되지 않아 실행할 수 없습니다. |
409 | PAYMENT_REVIEW_REQUIRED | A refund left an uncovered balance. Contact support or cover the balance before submitting tasks. |
409 | INSUFFICIENT_CREDITS | 사용 가능한 크레딧이 작업 가격보다 부족합니다. |
429 | RATE_LIMITED | 분당 작업 제출이 너무 많습니다. 나중에 다시 시도하세요. |
429 | EXPORT_RATE_LIMITED | Too many CSV exports this minute. Honor Retry-After. |
429 | CONCURRENCY_LIMITED | 완료되지 않은 작업이 너무 많습니다. 하나가 끝날 때까지 기다리세요. |
503 | EXECUTION_UNAVAILABLE | 현재 이 모델의 실행이 구성되어 있지 않습니다. |
429 | UPSTREAM_RATE_LIMITED | The model provider is rate limiting chat requests. Retry with backoff; nothing was charged. |
502 | UPSTREAM_ERROR | The model provider failed the chat request. Nothing was charged; retry later. |
503 | PLATFORM_BUDGET_EXCEEDED | This model is temporarily unavailable. Try again later. |
503 | EXECUTION_TEMPORARILY_UNAVAILABLE | 실행을 일시적으로 사용할 수 없습니다. 같은 Idempotency-Key로 다시 시도하세요. |
503 | AUTH_UNAVAILABLE | 인증을 일시적으로 사용할 수 없습니다. 나중에 다시 시도하세요. |
503 | API_UNAVAILABLE | API를 일시적으로 사용할 수 없습니다. 나중에 다시 시도하세요. |
MiniMax H3 API 자주 묻는 질문
Answers built from the model's schema and the Hermes AI API contract.
Can all H3 variants accept audio references?
No. Audio reference fields are listed for the multimodal reference-to-video variant; the other tasks have different input schemas.
What can the MiniMax H3 API do?
MiniMax H3 by MiniMax handles 이미지→동영상, 텍스트→동영상, 동영상→동영상 및 레퍼런스→동영상. The catalog lists 9 variants, each with its own model ID and input schema. Check the current availability before sending a request.
Which durations, resolutions and aspect ratios does MiniMax H3 support?
Across its variants, MiniMax H3 supports durations from 5 to 15 seconds, 480p, 768p 및 2K resolution 및 aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4 및 9:16. Each variant accepts its own subset; the variants table on this page lists them.
What input does MiniMax H3 accept?
A text prompt of up to 40,000 characters, plus 이미지, 동영상 또는 audio input (up to 9 images per request). Media fields take a public HTTPS URL or a media:<uuid> reference returned by POST /api/v1/media, so local files can be uploaded first. 알 수 없는 필드는 INVALID_MODEL_INPUT으로 거부됩니다.
How is MiniMax H3 priced and billed?
You pay per successful task from prepaid credits, with no subscription. The price depends on the variant and the specification you choose, such as resolution or duration; see the pricing table on this page or the pricing page. Credits are reserved when a task is accepted and charged only when it succeeds; a failed task returns the reservation to your balance.
Which MiniMax H3 variant should I choose?
For image to video, Max turbo image to video, Max image to video 및 Image to video differ in fields: Image to video adds aigc_watermark; for text to video, Max turbo text to video, Max text to video 및 Text to video differ in fields: Max turbo text to video adds aspectRatio; Max text to video adds ratio; Text to video adds ratio, aigc_watermark; for video to video, Regeneration text to video 및 Regeneration image to video differ in fields: Regeneration image to video adds firstFrameUrl, lastFrameUrl; for reference to video, use Multimodal reference to video. Pick the task first, then compare the tiers in the variants table.
How do I call the MiniMax H3 API from code?
Send POST https://api.hermes-ai.net/api/v1/jobs with the variant's model ID and an input object, then poll GET /api/v1/jobs/{id} until the status is succeeded or failed. The API section has cURL, JavaScript and Python examples generated from the schema.
Can I try MiniMax H3 without writing code?
Yes. Sign in and use the playground on this page: it sends the same request as the API with your session and charges the same price. Code needs an API key from the dashboard.
What happens when a task fails or I hit a rate limit?
A failed task is not charged and its reserved credits are returned. Too many submissions per minute return 429 RATE_LIMITED, and too many unfinished tasks return 429 CONCURRENCY_LIMITED; retry later or wait for a task to finish.