MiniMax

Overview

MiniMax is a Chinese AI company offering large language models alongside a rich suite of generative media — expressive text-to-speech, voice cloning and design, video generation, and music generation.

Official Website: https://www.minimaxi.com Documentation: https://platform.minimaxi.com/docs

Key features

• Chat & vision — Text generation with image understanding on supported models
• Advanced TTS — High-quality, emotionally expressive speech synthesis (see Audio)
• Voice cloning & design — Create and customize voices (see Audio)
• Video generation — Text-to-video and image-to-video (see Video)
• Music generation — Generate music from prompts (see Music)
• Image generation — Create images from text
• Bilingual — Strong Chinese and English capabilities

Using MiniMax with Yunxin

Address MiniMax models with the minimax/<model> prefix in the model field. You use the same Yunxin base URL (https://api.yuhuanstudio.com/v1) and your sk- API key. Media features are reached through the corresponding Yunxin endpoints — Audio, Video, and Music — using a MiniMax model id.

Capabilities vary by model. Query GET /v1/models to discover available models and what each one supports.

Usage example

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["YUNXIN_API_KEY"],
    base_url="https://api.yuhuanstudio.com/v1"
)

response = client.chat.completions.create(
    model="minimax/model-id",
    messages=[{"role": "user", "content": "你好！"}]
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.YUNXIN_API_KEY,
  baseURL: "https://api.yuhuanstudio.com/v1",
});

const response = await client.chat.completions.create({
  model: "minimax/model-id",
  messages: [{ role: "user", content: "你好！" }],
});

console.log(response.choices[0].message.content);

curl https://api.yuhuanstudio.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YUNXIN_API_KEY" \
  -d '{
    "model": "minimax/model-id",
    "messages": [{"role": "user", "content": "你好！"}]
  }'

Available models

Query the Models API for the current list and per-model capabilities:

curl "https://api.yuhuanstudio.com/v1/models?provider=minimax" \
  -H "Authorization: Bearer $YUNXIN_API_KEY"

Official resources

• MiniMax Website
• Platform
• Documentation