MiniMax M3 Preview API AI Agent

MiniMax M3 Preview Pricing

An AI agent workload (50K input + 5K output tokens, 100 tasks/day) costs approximately $23.63/month on Qubax.

Why use MiniMax M3 Preview for AI agents on Qubax?

• 🤖Autonomous agents that call APIs and external tools
• 🤖Multi-step reasoning for complex task completion
• 🤖Agent orchestration with LangChain, CrewAI, or custom frameworks
• 🤖Function calling for structured, reliable agent responses

About MiniMax M3 Preview

MiniMax M3 Preview is a 524K-context multimodal preview model for coding, reasoning, agents, tools, image understanding, and video understanding. It supports a 524K-token context window and up to 66K output tokens per request. Native capabilities include reasoning, vision, tool calling, streaming. On Qubax it is served by 26 independent sellers, so pricing stays competitive and uptime stays high.

MiniMax M3 Preview AI Agent — code example

from openai import OpenAI
import json

client = OpenAI(
    base_url="https://api.qubax.ai/v1",
    api_key="qbx_live_YOUR_KEY",
)

tools = [{
    "type": "function",
    "function": {
        "name": "get_weather",
        "parameters": {"type": "object", "properties": {"city": {"type": "string"}}},
    },
}]

resp = client.chat.completions.create(
    model="minimax-m3-preview",
    messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
    tools=tools,
)
call = resp.choices[0].message.tool_calls[0]
print(json.loads(call.function.arguments))  # -> {"city": "Tokyo"}

More MiniMax models on Qubax

MiniMax M3 Preview AI Agent FAQ