Models
MiniMax-M3
Model Overview
Direct supply
ChatStreamingVisionToolsThinkingMiniMax-M3：原生多模态、1M 上下文的 Frontier Coding 模型，Agentic 工作流与工具使用见长。
Input Modalities
Text, Image
Output Modalities
Text
Recommended for
Ideal for real-time multimodal conversations combining vision, tool use, and deep thinking.
Capabilities
Chat
Multi-turn conversational completions
Streaming
Tokens are delivered incrementally as they are generated
Vision
Accepts image input alongside text
Tool Use
Can call functions/tools defined in the request
Thinking
Produces an extended internal reasoning trace before the final answer
Supported Modes
Chat
Model Pricing
15% off
Pay-as-you-go
Full Pricing Breakdown
Every billed dimension for MiniMax-M3
Token Pricing
Cache Read$0.053per 1M tokens
Input$0.265per 1M tokens
Output$1.06per 1M tokens
Thinking$1.06per 1M tokens
Indicative pricing — final cost is confirmed at request time.
Context & Limits
- Context Window
- 1,000,000 tokens
API Code Example
OpenAI Compatible
import openai
client = openai.OpenAI(
base_url="https://api.modelsite.ai/v1",
api_key="sk-ms-...",
)
response = client.chat.completions.create(
model="minimax-m3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)