Saltar al contenido

MiniMaxVideo modelComprobando

MiniMax H3 API

Model IDminimax-h3-regeneration-image-to-video

MiniMax 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

Ejecuta MiniMax H3 en el playground

The form is the request body: every field shows its key. Sign in to run it; a run is billed like an API task.

Parámetros

Modelo
model

MiniMax H3Regeneration image to videominimax-h3-regeneration-image-to-video

Obligatorio
input.prompt

The final prompt actually sent to the model when generating the 768P source video. 1–40000 chars

input.firstFrameUrl

first frame image (same as generation) HTTPS image URL or media:<uuid>

input.baseVideoUrl

MiniMax-H3 768P source video (with audio track, 24fps, dims divisible by 32, area <=768x1344, 107-362 frames). ≤ 1 items · HTTPS video URL or media:<uuid>

input.resolution

Target resolution (2K only).

Opciones comunes
input.lastFrameUrl

last frame image (same as generation) HTTPS image URL or media:<uuid>

Estimated cost
Cargando precio…

Los créditos se reservan al aceptar una tarea y solo se cobran si tiene éxito. Las tareas fallidas liberan la reserva; los resultados sin confirmar siguen reservados hasta verificarse.

Vista previa de la solicitud

{"model": "minimax-h3-regeneration-image-to-video","input": {"resolution": "2K"}}

El playground web envía este cuerpo con tu sesión iniciada. Desde código, envía el mismo cuerpo con una clave de API.

Resultado

Run the request and the result appears here, with its status and cost.

Precios de MiniMax H3

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.

Cargando precio…
  • 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 retriesLos reintentos idempotentes con la misma clave no generan un segundo cargo.
  • Price changesEnvía expectedPriceMicros para rechazar la tarea con PRICE_CHANGED si el precio cambió después de mostrarlo.

Compara las variantes de MiniMax H3

Each variant has its own model ID and input schema. Pick the task first, then the tier. Additional fields are shown when variants differ.

  • Max turbo image to video

    minimax-h3-max-turbo-image-to-video

    Image to video; Texto, imagen; 5–15 s; 480p, 768p

  • Max turbo text to videoPredeterminado

    minimax-h3-max-turbo-text-to-video

    Text to video; Texto; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    aspectRatio
  • Max image to video

    minimax-h3-max-image-to-video

    Image to video; Texto, imagen; 5–15 s; 480p, 768p

  • Max text to video

    minimax-h3-max-text-to-video

    Text to video; Texto; 5–15 s; 480p, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    ratio
  • Image to video

    minimax-h3-image-to-video

    Image to video; Texto, imagen; 5–15 s; 2K, 768p

    aigc_watermark
  • Text to video

    minimax-h3-text-to-video

    Text to video; Texto; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

    ratioaigc_watermark
  • Regeneration text to video

    minimax-h3-regeneration-text-to-video

    Video to video; Texto, vídeo; 2K

  • Regeneration image to video

    minimax-h3-regeneration-image-to-video

    Video to video; Texto, imagen, vídeo; 2K

    firstFrameUrllastFrameUrl
  • Multimodal reference to video

    minimax-h3-multimodal-reference-to-video

    Reference to video; Texto, imagen, vídeo, audio; 5–15 s; 2K, 768p; 21:9, 16:9, 4:3, 1:1, 3:4, 9:16

Qué puede hacer MiniMax H3

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.

Capacidades

  • Up to 15 seconds

    Choose a length from 5 to 15 seconds.

    duration

    Every 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.

    firstFrameUrllastFrameUrl

    Variantes: 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.

    resolution

    Every 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.

    aspectRatioratio

    Variantes: 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.

    imageUrls

    Variantes: Multimodal reference to video

  • Video input

    Accepts a source video as input.

    baseVideoUrlvideoUrls

    Variantes: Regeneration text to video, Regeneration image to video, Multimodal reference to video

  • Audio input

    Accepts reference audio as input.

    audioUrls

    Variantes: Multimodal reference to video

Casos de uso

  1. Generate a scene

    Describe the visual action and sound for a text-to-video task.

  2. Create from references

    Use the multimodal variant to supply supported reference media.

  3. Regenerate a clip

    Select a regeneration variant when you have a base video and follow its input requirements.

Llama a MiniMax H3 desde código

Every image, video and music model uses the same asynchronous job API: submit a task, then poll for the result.

  1. 1

    Crea una clave de API

    In the dashboard, with the jobs:create and jobs:read scopes. Claves de API
  2. 2

    Enviar una tarea

    POST /api/v1/jobs with the model ID and an input object. The response is 202 with a task ID.
  3. 3

    Poll for the result

    GET /api/v1/jobs/{id} until the status is succeeded, then download the output URLs.

Solicitud mínima

Required fields only, generated from the schema of Regeneration image to video. Set HERMES_API_KEY in your environment.

Model ID
minimax-h3-regeneration-image-to-video
Endpoint
https://api.hermes-ai.net/api/v1/jobs
Full task API reference
# 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-regeneration-image-to-video",
  "input": {
    "prompt": "A lighthouse on a rocky coast at sunrise, soft light",
    "firstFrameUrl": "https://example.com/input.png",
    "baseVideoUrl": "https://example.com/input.mp4",
    "resolution": "2K"
  }
}'

# 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"

Parámetros de entrada

Fields of Regeneration image to video (minimax-h3-regeneration-image-to-video). Los campos desconocidos se rechazan con INVALID_MODEL_INPUT.

CampoTipoObligatorioPredeterminadoValores permitidos y restricciones
prompt
stringobligatorio—

The final prompt actually sent to the model when generating the 768P source video.

1–40000 chars

firstFrameUrl
stringobligatorio—

first frame image (same as generation)

HTTPS image URL or media:<uuid>

lastFrameUrl
stringopcional—

last frame image (same as generation)

HTTPS image URL or media:<uuid>

baseVideoUrl
stringobligatorio—

MiniMax-H3 768P source video (with audio track, 24fps, dims divisible by 32, area <=768x1344, 107-362 frames).

≤ 1 items, HTTPS video URL or media:<uuid>

resolution
stringobligatorio"2K"

Target resolution (2K only).

Uno de: "2K"

Sube primero un archivo local

Sustituye la URL de ejemplo por la referencia multimedia devuelta.

POST /api/v1/media
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
EncabezadoValorNotas
AuthorizationBearer <API key>O envía la clave en x-api-key.
Content-Typeapplication/json
Idempotency-Key<unique string ≤128>Obligatorio. Reutilízalo solo para reintentar la misma solicitud.
CampoTipoNotas
idstringID de tarea de Hermes AI. Úsalo para consultar.
modelstringSlug del modelo.
statusstringConsulta los estados de la tarea.
errorCodestring | nullSe establece cuando una tarea falla o requiere revisión.
priceMicrosintegerCotización fijada al aceptarla, en micro-unidades de USD.
currency"USD"
createdAt / updatedAtstringMarcas de tiempo ISO 8601.
assets[]array{ id, type, url?, text? }. url es un enlace /api/v1/results/<uuid> del mismo origen.
replayedbooleanSolo al enviar. true cuando coincide un reintento idempotente.
EstadoFinalSignificado
queuednoAceptada y a la espera de un trabajador.
submittingnoEnviándose al proveedor del modelo.
runningnoEl modelo está generando.
succeededsíTerminada. Los resultados están en assets.
failedsíTerminada sin resultado. La reserva se libera.
reconciliation_requiredsíThe result is being verified. Keep the task ID and do not resubmit automatically.
HTTPCódigoSignificado y acción
401AUTH_REQUIREDFalta la clave de API o la sesión, o no es válida.
403INSUFFICIENT_SCOPELa clave de API no tiene el permiso que necesita este endpoint.
403PERMISSION_DENIEDEsta credencial no puede realizar la operación.
429API_KEY_RATE_LIMITEDSe alcanzó el límite de frecuencia de la clave de API. Respeta Retry-After.
429API_KEY_USAGE_EXCEEDEDLa clave de API alcanzó su límite de uso. Crea una clave nueva.
400INVALID_REQUESTEl cuerpo no es un objeto JSON o falta un valor obligatorio.
400INVALID_IDEMPOTENCY_KEYIdempotency-Key debe tener entre 1 y 128 caracteres ASCII imprimibles.
400INVALID_MODEL_INPUTinput no coincide con el esquema del modelo (campo desconocido, campo obligatorio ausente o valor no válido).
400 / 413INPUT_TOO_LARGEEl cuerpo de la solicitud supera los 256 KB. Sube primero los archivos multimedia y envía una referencia.
404REQUEST_NOT_FOUNDNo chat request with this ID belongs to your account.
404MODEL_NOT_FOUNDNingún modelo tiene este slug.
404JOB_NOT_FOUNDNinguna tarea con este ID pertenece a tu cuenta.
409IDEMPOTENCY_CONFLICTEsta Idempotency-Key se usó con otra entrada. Usa una clave nueva para una solicitud nueva.
409PRICE_CHANGEDEl precio difiere de expectedPriceMicros. Obtén el precio y vuelve a confirmarlo.
409MODEL_PRICE_UNAVAILABLEEste modelo aún no tiene precio configurado, por lo que no puede ejecutarse.
409PAYMENT_REVIEW_REQUIREDA refund left an uncovered balance. Contact support or cover the balance before submitting tasks.
409INSUFFICIENT_CREDITSLos créditos disponibles no cubren el precio de la tarea.
429RATE_LIMITEDDemasiados envíos de tareas por minuto. Vuelve a intentarlo más tarde.
429EXPORT_RATE_LIMITEDToo many CSV exports this minute. Honor Retry-After.
429CONCURRENCY_LIMITEDDemasiadas tareas sin terminar. Espera a que termine alguna.
503EXECUTION_UNAVAILABLELa ejecución no está configurada para este modelo en este momento.
429UPSTREAM_RATE_LIMITEDThe model provider is rate limiting chat requests. Retry with backoff; nothing was charged.
502UPSTREAM_ERRORThe model provider failed the chat request. Nothing was charged; retry later.
503PLATFORM_BUDGET_EXCEEDEDThis model is temporarily unavailable. Try again later.
503EXECUTION_TEMPORARILY_UNAVAILABLELa ejecución no está disponible temporalmente. Reintenta con la misma Idempotency-Key.
503AUTH_UNAVAILABLELa autenticación no está disponible temporalmente. Vuelve a intentarlo más tarde.
503API_UNAVAILABLELa API no está disponible temporalmente. Vuelve a intentarlo más tarde.

Preguntas frecuentes sobre la API de MiniMax H3

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 imagen a vídeo, texto a vídeo, vídeo a vídeo y referencia a vídeo. 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 y 2K resolution y aspect ratios 21:9, 16:9, 4:3, 1:1, 3:4 y 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 imagen, vídeo o 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. Los campos desconocidos se rechazan con INVALID_MODEL_INPUT.

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 y 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 y 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 y 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.