Chat Completions API

{ "content": "Hello" }

{
    "content": [
        { "type": "text", "text": "Describe this image" },
        { "type": "image_url", "image_url": { "url": "data:image/png;base64,..." } },
        { "type": "video_url", "video_url": { "url": "data:video/mp4;base64,..." } }
    ]
}

{ "type": "image_url", "image_url": "data:image/png;base64,..." }

{
    "id": "chatcmpl-6adb0d430e590c70159c6ca1",
    "object": "chat.completion",
    "created": 1792740680,
    "model": "kimi-k3.1-pro",
    "choices": [
        {
            "index": 0,
            "message": {
                "content": "1 + 1 = 2",
                "role": "assistant",
                "reasoning_content": "The user is asking a very simple math question: \"What is 1+1?\"\n\nThis is as basic as it gets. The answer is 2. There's no need for any elaborate explanation, headers, bullet points, or lengthy response. A simple, direct answer is appropriate here.\n\nI could just say \"2\" or \"1+1 = 2\" — keeping it brief and conversational since this is a casual chat context."
            },
            "finish_reason": "stop"
        }
    ],
    "usage": {
        "completion_tokens": 112,
        "prompt_tokens": 373,
        "total_tokens": 485,
        "completion_tokens_details": {
            "reasoning_tokens": 90
        },
        "prompt_tokens_details": {
            "cache_write_tokens": 256
        }
    }
}

data: {"id":"chatcmpl-6adb0ef47c3c1358b6a07603","object":"chat.completion.chunk","created":1792741110,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

data: {"id":"chatcmpl-6adb0ef47c3c1358b6a07603","object":"chat.completion.chunk","created":1792741110,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

...

data: {"id":"chatcmpl-6adb0ef47c3c1358b6a07603","object":"chat.completion.chunk","created":1792741110,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"content":"1"},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

...

data: {"id":"chatcmpl-6adb0ef47c3c1358b6a07603","object":"chat.completion.chunk","created":1792741110,"model":"kimi-k3.1-pro","choices":[],"usage":{"prompt_tokens":373,"completion_tokens":93,"total_tokens":466,"completion_tokens_details":{"reasoning_tokens":71},"prompt_tokens_details":{"cache_write_tokens":256}}}

data: [DONE]

{
    "model": "kimi-k3.1-pro",
    "messages": [{"role": "user", "content": "Hello"}],
    "prompt_cache_options": { "mode": "implicit", "ttl": "1h" }
}

messages = [
    {"role": "system", "content": "You are Kimi."},
    {"role": "user", "content": "Hello, my name is Li Lei."}
]

completion = client.chat.completions.create(model="kimi-k3.1-pro", messages=messages)
reply = completion.choices[0].message

# Preserve the full assistant reply, including reasoning_content and any tool_calls
messages.append(reply.model_dump(exclude_none=True))
messages.append({"role": "user", "content": "What is 1+1?"})

completion = client.chat.completions.create(model="kimi-k3.1-pro", messages=messages)
print(completion.choices[0].message.content)

{
  "model": "kimi-k3.1-pro",
  "messages": [
    {"role": "system", "content": "Please output JSON containing title, author, and summary fields."},
    {"role": "user", "content": "Summarize this article: Recursion solves problems by breaking them into smaller instances of the same problem, with a base case that ends the calls."}
  ],
  "response_format": {"type": "json_object"}
}

{
  "model": "kimi-k3.1-pro",
  "messages": [{"role": "user", "content": "What is the weather in Beijing today?"}],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "Get the weather for a given city",
        "parameters": {
          "type": "object",
          "properties": {
            "city": {"type": "string", "description": "City name"}
          },
          "required": ["city"]
        }
      }
    }
  ]
}

{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "",
      "reasoning_content": "The user is asking about the weather in Beijing today. I have a tool available called `get_weather` that can get the weather for a given city. Let me use it to find the weather in Beijing.",
      "tool_calls": [
        {
          "id": "get_weather_0_4d9e2559",
          "type": "function",
          "function": {
            "arguments": "{\"city\":\"Beijing\"}",
            "name": "get_weather"
          }
        }
      ]
    },
    "finish_reason": "tool_calls"
  }]
}

{"role": "tool", "tool_call_id": "get_weather_0_4d9e2559", "content": "Sunny, 25°C"}

{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": "1 + 1 = 2",
      "reasoning_content": "The user is asking a very simple math question: \"What is 1+1?\"\n\nThis is as basic as it gets. The answer is 2. There's no need for any elaborate explanation, headers, bullet points, or lengthy response. A simple, direct answer is appropriate here.\n\nI could just say \"2\" or \"1+1 = 2\" — keeping it brief and conversational since this is a casual chat context."
    }
  }]
}

completion = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[{"role": "user", "content": "Explain what recursion is."}],
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in completion:
    if chunk.usage is not None:
        print("\nusage:", chunk.usage.model_dump())
    if not chunk.choices:
        continue
    delta = chunk.choices[0].delta
    reasoning: str = getattr(delta, "reasoning_content", None) or ""
    if reasoning:
        print(reasoning, end="")
    if delta.content:
        print(delta.content, end="")

data: {"id":"chatcmpl-6adb0efaa6c470a707811b01","object":"chat.completion.chunk","created":1792741114,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

data: {"id":"chatcmpl-6adb0efaa6c470a707811b01","object":"chat.completion.chunk","created":1792741114,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"reasoning_content":"The"},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

...

data: {"id":"chatcmpl-6adb0efaa6c470a707811b01","object":"chat.completion.chunk","created":1792741114,"model":"kimi-k3.1-pro","choices":[{"index":0,"delta":{"content":"#"},"finish_reason":null}],"system_fingerprint":"fpv0_e7278693"}

...

data: {"id":"chatcmpl-6adb0efaa6c470a707811b01","object":"chat.completion.chunk","created":1792741114,"model":"kimi-k3.1-pro","choices":[],"usage":{"prompt_tokens":90,"completion_tokens":1524,"total_tokens":1614,"completion_tokens_details":{"reasoning_tokens":1007},"prompt_tokens_details":{"cache_write_tokens":0}}}

data: [DONE]

stream=True,
stream_options={"include_usage": True}

completion = client.chat.completions.create(
    model="kimi-k3.1-pro",
    messages=[
        {"role": "user", "content": "Implement quicksort in Python."},
        {"role": "assistant", "content": "```python\n", "partial": True}
    ]
)