Kimi K2 Thinking API AI Agent

Kimi K2 Thinking Pricing

An AI agent workload (50K input + 5K output tokens, 100 tasks/day) costs approximately $1.66/month on Qubax.

Why use Kimi K2 Thinking 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 Kimi K2 Thinking

Kimi K2 Thinking is a text generation model available on Qubax. It supports a 256K-token context window and up to 66K output tokens per request. Native capabilities include reasoning, tool calling, structured output, streaming. On Qubax it is served by 282 independent sellers, so pricing stays competitive and uptime stays high.

Kimi K2 Thinking 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="kimi-k2-thinking",
    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 Moonshot AI models on Qubax

Kimi K2 Thinking AI Agent FAQ