PopNowAPI 文档
正文

MiniMax H3 Max API 调用参考

出片快,自带环境声、音效和配乐

用一个 PopNow API 密钥,就能在自己的代码里调用 MiniMax H3 Max。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分,以及一段可以直接粘进终端运行的请求。

参数说明直接取自型号的输入 schema,暂时只有英文。

一览

出品方
MiniMax
产出
视频
起价
7.5 积分 每秒成片 ($0.075)
一般耗时
约 31 秒

1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用,完成后按实际用量结算、向上取整到整积分,多冻的退回;失败的任务不扣积分。想在运行前知道确切数字,先调 POST /api/v1/jobs/quote。

生成视频

minimax/h3-max/text-to-video

价格

选项积分 (每秒成片)美元
480p7.5$0.075
768p12$0.12

参数

字段类型默认值取值范围作用
prompt必填string—最多 7000 个字符Describe the subject, action, camera, and mood of the shot.
aspect_ratio可选string1:121:9, 16:9, 4:3, 1:1, 3:4, 9:16Output aspect ratio.
duration_seconds可选integer85 到 15Requested output length in seconds, from 5 to 15.
resolution可选string768p480p, 768pOutput resolution.
enable_prompt_expansion可选booleanfalse—Expand the prompt into a fuller description before generating. Requests with it on add a flat per-request prompt-expansion fee.

请求示例

这段请求原样就能运行,没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

POST /api/v1/jobs/createTask
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/h3-max/text-to-video",
  "input": {
    "prompt": "A paper boat drifts down a rain-soaked street at dusk, neon signs reflecting in the water, slow tracking shot at ground level",
    "enable_prompt_expansion": false,
    "resolution": "768p",
    "duration_seconds": 8
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果,或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

图生视频

minimax/h3-max/image-to-video

价格

选项积分 (每秒成片)美元
480p7.5$0.075
768p12$0.12

参数

字段类型默认值取值范围作用
image_url必填string (uri)——Opening frame. It fixes the composition and the subject the clip starts from.
prompt必填string—最多 7000 个字符Describe what happens after the opening frame: the action, the camera, and the mood.
last_image_url可选string (uri)——Optional closing frame the clip should resolve to. It may only be sent together with an opening frame.
duration_seconds可选integer85 到 15Requested output length in seconds, from 5 to 15.
resolution可选string768p480p, 768pOutput resolution.
enable_prompt_expansion可选booleanfalse—Expand the prompt into a fuller description before generating. Requests with it on add a flat per-request prompt-expansion fee.

请求示例

这段请求原样就能运行,没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

示例里的 image_url 用的是 PopNow 的示例素材,换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。

POST /api/v1/jobs/createTask?wait=60
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask?wait=60" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/h3-max/image-to-video",
  "input": {
    "prompt": "He lands softly on the rooftop, laughs and turns toward the camera while the balloons sway in the evening breeze; slow push-in",
    "image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
    "enable_prompt_expansion": false,
    "resolution": "768p",
    "duration_seconds": 8
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果,或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

视频续写

minimax/h3-max/video-extend

价格

选项积分 (每秒成片)美元
480p7.5$0.075
768p12$0.12

参数

字段类型默认值取值范围作用
prompt必填string—最多 7000 个字符Describe what happens next: the action that follows, the camera move and the sound.
video_url必填string (uri)——The clip to continue: MP4, MOV or WebM, up to 60 seconds. Its last frame opens the new segment, and the result is your clip with the new segment joined on.
last_image_url可选string (uri)——Optional target end frame: the new segment closes on this image.
duration_seconds可选integer85 到 15Length of the new segment in seconds, from 5 to 15. The source clip is added on top and is not billed.
resolution可选string768p480p, 768pResolution of the new segment. It sets how sharp the new part is generated; match your source clip.
enable_prompt_expansion可选booleanfalse—Expand the prompt into a fuller description before generating. Requests with it on add a flat per-request prompt-expansion fee.

请求示例

这段请求原样就能运行,没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。

示例里的 video_url 用的是 PopNow 的示例素材,换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。

POST /api/v1/jobs/createTask
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
  -H "Authorization: Bearer $POPNOW_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "minimax/h3-max/video-extend",
  "input": {
    "prompt": "The flowers keep opening while the camera slowly pulls back to reveal a sunlit meadow",
    "video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
    "enable_prompt_expansion": false,
    "resolution": "768p",
    "duration_seconds": 8
  }
}'

响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果,或者在请求里加上 callBackUrl 等通知。

GET /api/v1/jobs/recordInfo
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
  -H "Authorization: Bearer $POPNOW_API_KEY"

接下来

本页内容