Back to Models

MiniMax M3

可用
MiniMax-M3

MiniMax M3 — reasoning model with strong multi-turn recall. Verified over a 10-turn session: 6/6 factual checks, p50 3.6s.

Try in Playground

Technical Specifications

上下文长度1000K tokens
最大输出8K tokens
最低输入价$0.24/1M tokens
最低输出价$0.96/1M tokens

Capabilities

chatcodefunction_calling

价格

输入$0.24/1M
输出$0.96/1M
缓存$0.05/1M

Code Examples

curl https://api.tokligence.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "MiniMax-M3",
    "messages": [
      {
        "role": "user",
        "content": "Hello, how are you?"
      }
    ],
    "max_tokens": 1024
  }'

Ready to use MiniMax M3?

Try it out in our interactive playground or integrate it into your application with just a few lines of code.

Open PlaygroundGet API Key