MiniMax H3
minimax/minimax-h3MiniMax H3 是开放通用的多模态视频模型,可以统一理解文本、图片、视频和音频输入,完成视频生成、参考创作与视频编辑。
- Modalities
- Public starting price
- Priced by multiple attributes
- Added to catalog
- Aug 5, 2026
Online Inference
Online Inference
This model has no verifiable input schema, so inference is disabled.
Task History
Task history
Only generation records from the last seven days are available.
Sign in to view your task history.
Sign in to view task historyFilled when you open this page. The default query uses the current model ID; leave blank for records from all models.
| Task ID | Model | Completion status | Created | Duration | Credits consumed | Artifact |
|---|
API Call
MiniMax H3 code examples and API guide
Modelmesh normalizes requests and responses across service providers behind one consistent API.
Modelmesh provides an OpenAI-compatible Completion API for more than 300 models and service providers. Call it directly, through the OpenAI SDK, or with supported third-party SDKs.
Modelmesh-specific request headers in these examples are optional. When supplied, your application can appear on the Modelmesh rankings.
#!/usr/bin/env bash
set -euo pipefail
API_KEY="$SSY_API_KEY"
curl --fail-with-body --silent --show-error --location \
--request POST \
"https://router.shengsuanyun.com/api/v1/tasks/generations" \
--header "Content-Type: application/json" \
--header "Authorization: Bearer ${API_KEY}" \
--data '{
"model": "minimax/minimax-h3"
}'
#!/usr/bin/env bash
set -euo pipefail
API_KEY="$SSY_API_KEY"
REQUEST_ID="${SSY_REQUEST_ID:?Set SSY_REQUEST_ID to the ID returned by task submission}"
curl --fail-with-body --silent --show-error --location \
--request GET \
"https://router.shengsuanyun.com/api/v1/tasks/generations/${REQUEST_ID}" \
--header "Authorization: Bearer ${API_KEY}"
Pricing
Pricing Details
All prices shown in CNY- 参考图片(前 5 张免费)
- ¥0.2/张
- 每秒输出
- 2K:¥0.8/秒
- 768P:¥0.5/秒
- 每秒输入
- 2K:¥0.8/秒
- 768P:¥0.5/秒