┌─────────────────────────────────────────────────────────────────┐
│                    Moonshot AI Platform                          │
│                  platform.moonshot.ai                            │
└─────────────────────────────────────────────────────────────────┘
                              │
        ┌─────────────────────┼─────────────────────┐
        │                     │                     │
        ▼                     ▼                     ▼
┌───────────────┐    ┌───────────────┐    ┌───────────────┐
│  Kimi K2      │    │ moonshot-v1   │    │   Tool Use    │
│  (Latest)     │    │  (Legacy)     │    │               │
├───────────────┤    ├───────────────┤    ├───────────────┤
│ • 1T params   │    │ • v1-8k       │    │ • Functions   │
│ • 32B active  │    │ • v1-32k      │    │ • Web Search  │
│ • 128K-256K   │    │ • v1-128k     │    │ • Code Exec   │
│ • MoE arch    │    │               │    │ • Custom      │
└───────────────┘    └───────────────┘    └───────────────┘
        │                     │                     │
        └─────────────────────┼─────────────────────┘
                              │
                              ▼
                    ┌───────────────────┐
                    │   API Endpoints   │
                    ├───────────────────┤
                    │ • OpenAI compat   │
                    │ • Anthropic compat│
                    │ • Streaming       │
                    │ • Tool calling    │
                    └───────────────────┘

Architecture: Mixture-of-Experts (MoE)
Total Parameters: 1 Trillion
Activated Parameters: 32 Billion per token
Layers: 61 (including 1 dense layer)
Experts: 384 total, 8 selected per token
Attention: MLA (Multi-head Latent Attention)
Activation: SwiGLU
Vocabulary: 160K tokens
Context: 128K tokens (256K for 0905-preview)
Training Data: 15.5T tokens

export MOONSHOT_API_KEY="your-api-key-here"

# Optional: Use China endpoint
export MOONSHOT_API_BASE="https://api.moonshot.cn/v1"

from openai import OpenAI

client = OpenAI(
    api_key="your-api-key",
    base_url="https://api.moonshot.ai/v1"
)

response = client.chat.completions.create(
    model="kimi-k2-0905-preview",
    messages=[
        {"role": "system", "content": "You are Kimi, an AI assistant created by Moonshot AI."},
        {"role": "user", "content": "Explain quantum computing in simple terms."}
    ],
    temperature=0.6,  # Recommended
    max_tokens=1024
)

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

curl https://api.moonshot.ai/v1/chat/completions \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2-0905-preview",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

{
  "messages": [
    {"role": "system", "content": "System prompt"},
    {"role": "user", "content": "User message"},
    {"role": "assistant", "content": "Previous response"},
    {"role": "user", "content": [
      {"type": "text", "text": "Multimodal content"}
    ]}
  ]
}

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "kimi-k2-0905-preview",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "Response text"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 50,
    "completion_tokens": 100,
    "total_tokens": 150
  }
}

tools = [
    {
        "type": "function",
        "function": {
            "name": "get_weather",
            "description": "Get current weather for a city",
            "parameters": {
                "type": "object",
                "required": ["city"],
                "properties": {
                    "city": {
                        "type": "string",
                        "description": "City name"
                    },
                    "unit": {
                        "type": "string",
                        "enum": ["celsius", "fahrenheit"],
                        "description": "Temperature unit"
                    }
                }
            }
        }
    },
    {
        "type": "function",
        "function": {
            "name": "search_web",
            "description": "Search the web for information",
            "parameters": {
                "type": "object",
                "required": ["query"],
                "properties": {
                    "query": {
                        "type": "string",
                        "description": "Search query"
                    }
                }
            }
        }
    }
]

response = client.chat.completions.create(
    model="kimi-k2-0905-preview",
    messages=[
        {"role": "user", "content": "What's the weather in Tokyo?"}
    ],
    tools=tools,
    tool_choice="auto",
    temperature=0.6
)

# Check if model wants to call a tool
message = response.choices[0].message
if message.tool_calls:
    for tool_call in message.tool_calls:
        print(f"Function: {tool_call.function.name}")
        print(f"Arguments: {tool_call.function.arguments}")

import json

def execute_tool(name: str, args: dict) -> str:
    """Execute tool and return result."""
    if name == "get_weather":
        return json.dumps({"temp": 22, "condition": "sunny"})
    elif name == "search_web":
        return json.dumps({"results": ["Result 1", "Result 2"]})
    return json.dumps({"error": "Unknown tool"})

messages = [{"role": "user", "content": "What's the weather in Tokyo?"}]

while True:
    response = client.chat.completions.create(
        model="kimi-k2-0905-preview",
        messages=messages,
        tools=tools,
        tool_choice="auto",
        temperature=0.6
    )

    message = response.choices[0].message
    messages.append(message)

    if not message.tool_calls:
        # No more tool calls, done
        print(message.content)
        break

    # Execute each tool call
    for tool_call in message.tool_calls:
        result = execute_tool(
            tool_call.function.name,
            json.loads(tool_call.function.arguments)
        )
        messages.append({
            "role": "tool",
            "tool_call_id": tool_call.id,
            "content": result
        })

stream = client.chat.completions.create(
    model="kimi-k2-0905-preview",
    messages=[{"role": "user", "content": "Write a poem about AI"}],
    stream=True,
    temperature=0.6
)

for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.MOONSHOT_API_KEY,
  baseURL: 'https://api.moonshot.ai/v1'
});

async function chat() {
  const stream = await client.chat.completions.create({
    model: 'kimi-k2-0905-preview',
    messages: [{ role: 'user', content: 'Hello!' }],
    stream: true
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
  }
}

curl https://api.moonshot.ai/v1/chat/completions \
  -H "Authorization: Bearer $MOONSHOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "kimi-k2-0905-preview",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

from litellm import completion

response = completion(
    model="moonshot/kimi-k2-0905-preview",
    messages=[{"role": "user", "content": "Hello"}]
)

model_list:
  - model_name: kimi-k2
    litellm_params:
      model: moonshot/kimi-k2-0905-preview
      api_key: os.environ/MOONSHOT_API_KEY

  - model_name: kimi-128k
    litellm_params:
      model: moonshot/moonshot-v1-128k
      api_key: os.environ/MOONSHOT_API_KEY

from anthropic import Anthropic

client = Anthropic(
    api_key="your-moonshot-key",
    base_url="https://api.moonshot.ai/v1"
)

# Note: Temperature mapping
# real_temperature = request_temperature * 0.6
response = client.messages.create(
    model="kimi-k2-0905-preview",
    messages=[{"role": "user", "content": "Hello!"}],
    max_tokens=1024,
    temperature=1.0  # Will become 0.6 internally
)

# Recommended default
temperature = 0.6

# For creative tasks
temperature = 0.8

# For factual/deterministic tasks
temperature = 0.3

# Default system prompt (good starting point)
system_prompt = "You are Kimi, an AI assistant created by Moonshot AI."

# Custom for specific tasks
system_prompt = """You are a coding assistant.
Provide clean, well-documented code with explanations.
Use Python unless otherwise specified."""

# For documents up to 256K tokens
response = client.chat.completions.create(
    model="kimi-k2-0905-preview",  # Supports 256K
    messages=[
        {"role": "system", "content": "Analyze the following document."},
        {"role": "user", "content": very_long_document}
    ],
    temperature=0.3  # Lower for analysis tasks
)

Error: 401 Unauthorized

Error: 429 Too Many Requests

Error: Context length exceeded

Error: Invalid tool definition