minimax-h3-maxCompare minimax-h3-max API pricing, supported endpoints, capabilities and access options on Modelsell.
| Tier | Video output/ second | Image In/ image | Reference video/ second |
|---|---|---|---|
480P | $0.05 | $0.074 | $0.0553 |
| Free reference images: 2 | |||
Other resolutions | $0.08 | $0.074 | $0.143 |
| Free reference images: 2 | |||
Free reference images: 2
Free reference images: 2
ABAB tokenizerScores on standardized evaluations. Higher percentages are better — and rank percentile shows
Metrics sourced fromArtificial Analysis 2026-09-30·MiniMax H3 Max
This model is not included in the current benchmark snapshot.
Missing models or measurements are not zero scores.
Benchmark charts preserve the source model selection and reasoning settings. Missing models or measurements are not zero scores, and benchmark cost or speed is not this site’s service commitment.
MiniMax H3 Max 提供 480P、768P 视频输出,最短生成时长为 5 秒。通过 content 指定文本与参考素材;可使用 extra.prompt_expansion_mode 选择 disabled、balanced 或 quality,默认为 balanced。素材、分辨率和其他参数由供应商执行最终校验。
以下为 2026-10-28 供应商目录的美元标准价;组织采购折扣不用于此处的基准计费。实际账单还会应用账户所属分组的既有倍率。成功任务按最终用量结算,失败任务按网关任务流程退款,查询不重复收费。
480P 输出 $0.05/秒,768P 输出 $0.08/秒;输入参考视频分别为 $0.0553/秒和 $0.143/秒。参考图片前 2 张免费,超出部分 $0.074/张。输入与输出视频分开计量,读取 task.metadata.usage.input_seconds 和 output_seconds;图片数量读取 input_image_count。
向网关 /v1/video/generate 发送以下 JSON,并使用自己的网关令牌鉴权:
{
"model": "minimax-h3-max",
"content": [
{
"type": "text",
"text": "A red ceramic teapot rests on a wooden table in warm morning sunlight. No people, no text."
}
],
"resolution": "480P",
"duration": 5,
"ratio": "16:9",
"extra": {
"prompt_expansion_mode": "balanced"
}
}
任务为异步处理。创建响应中的 task.id 是网关公开任务 ID;使用 GET /v1/video/tasks/{task_id} 查询,每 10–15 秒一次。成功视频地址在 task.outputs,最终计量在 task.metadata.usage。此任务空间与 /v2 原生协议不同。
也可调用 POST /v1/videos 或 POST /v1/video/generations,使用 model: "minimax-h3-max"、prompt、seconds: "5"、size: "480P"。通过 metadata.content 指定完整素材数组,通过 metadata.extra 传入平台扩展参数。
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| official | Unlimited | Unlimited | Unlimited |
| MiniMax | Unlimited | Unlimited | Unlimited |
No restriction
Compare minimax-h3-max API pricing, supported endpoints, capabilities and access options on Modelsell.
Create an API key with access to minimax-h3-max, then use the exact model ID and a supported endpoint from the API access section. Request fields depend on the selected endpoint.
Pricing depends on the selected provider group and the model billing unit. The current input, output, request, or media prices are shown on this page before sign-up.
Start with the use cases and prompting guidance on this page, then evaluate the model with representative inputs from your project.
