> ## Documentation Index
> Fetch the complete documentation index at: https://docs.samuraiapi.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Create Chat Completion

> Generate a model response for a conversation. Supports 200+ models, streaming, function calling, and vision.

<ParamField body="model" type="string" required>
  The model ID to use. See the [Models reference](/reference/models) for all available IDs.

  Popular values: `gpt-4o`, `gpt-4o-mini`, `claude-3-5-sonnet-20241022`, `gemini-2.0-flash`, `deepseek-chat`
</ParamField>

<ParamField body="messages" type="array" required>
  Array of conversation messages. Each message has a `role` (`system`, `user`, `assistant`) and `content`.
</ParamField>

<ParamField body="temperature" type="number" default="1">
  Sampling temperature from `0` to `2`. Lower = more deterministic, higher = more creative.
</ParamField>

<ParamField body="max_tokens" type="integer">
  Maximum tokens to generate. If omitted, uses the model's default.
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  If `true`, streams partial tokens via Server-Sent Events. See [Streaming](/api/streaming).
</ParamField>

<ParamField body="top_p" type="number" default="1">
  Nucleus sampling. Only sample from top `p` probability mass. Use `temperature` OR `top_p`, not both.
</ParamField>

<ParamField body="frequency_penalty" type="number" default="0">
  Penalizes tokens based on how often they appear in the text so far. Range: `-2.0` to `2.0`.
</ParamField>

<ParamField body="presence_penalty" type="number" default="0">
  Penalizes tokens based on whether they have appeared at all so far. Range: `-2.0` to `2.0`.
</ParamField>

<ParamField body="stop" type="string | array">
  Up to 4 stop sequences. The API will stop generating further tokens when it encounters any of these.
</ParamField>

<ParamField body="n" type="integer" default="1">
  Number of completions to generate. Each counts toward your usage.
</ParamField>

<ParamField body="user" type="string">
  A unique identifier for your end-user. Helps with abuse monitoring.
</ParamField>

<RequestExample>
  ```bash cURL theme={null}
  curl https://www.samuraiapi.in/v1/chat/completions \
    -H "Authorization: Bearer $SAMURAI_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-4o",
      "messages": [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of Japan?"}
      ],
      "temperature": 0.7,
      "max_tokens": 150
    }'
  ```

  ```python Python theme={null}
  from openai import OpenAI

  client = OpenAI(
      api_key="sk-samurai-YOUR_KEY",
      base_url="https://www.samuraiapi.in/v1"
  )

  response = client.chat.completions.create(
      model="gpt-4o",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "What is the capital of Japan?"}
      ],
      temperature=0.7,
      max_tokens=150
  )

  print(response.choices[0].message.content)
  # => "Tokyo is the capital of Japan."
  ```

  ```javascript Node.js theme={null}
  import OpenAI from 'openai';

  const client = new OpenAI({
    apiKey: process.env.SAMURAI_API_KEY,
    baseURL: 'https://www.samuraiapi.in/v1'
  });

  const response = await client.chat.completions.create({
    model: 'claude-3-5-sonnet-20241022',
    messages: [
      { role: 'system', content: 'You are a helpful assistant.' },
      { role: 'user', content: 'What is the capital of Japan?' }
    ],
    temperature: 0.7
  });

  console.log(response.choices[0].message.content);
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "chatcmpl-abc123xyz",
    "object": "chat.completion",
    "created": 1715000000,
    "model": "gpt-4o",
    "choices": [
      {
        "index": 0,
        "message": {
          "role": "assistant",
          "content": "Tokyo is the capital of Japan. It is also the most populous metropolitan area in the world."
        },
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 28,
      "completion_tokens": 22,
      "total_tokens": 50
    }
  }
  ```

  ```json 401 theme={null}
  {
    "error": {
      "type": "auth_error",
      "message": "Invalid API key provided.",
      "code": 401
    }
  }
  ```

  ```json 429 theme={null}
  {
    "error": {
      "type": "rate_limit_exceeded",
      "message": "Daily request limit reached. Resets at midnight UTC.",
      "code": 429
    }
  }
  ```
</ResponseExample>