> ## Documentation Index
> Fetch the complete documentation index at: https://nusaai-edit.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Create a Message

<Card icon="key" href="https://app.neosantara.xyz/api-keys" title="Get your free API key" horizontal>
  Start with **10,000 Monthly Token Limit** on our Free Plan. **No credit card required.** Your tokens automatically reset on the 1st of each month.
</Card>

<ParamField path="model" type="string" required>
  The model ID to use for the request.

  **Example:** `"garda-beta-mini"`, `"nusantara-base"`
</ParamField>

<ParamField path="messages" type="array[object]" required>
  Array of message objects with alternating user/assistant roles.

  <Expandable title="message structure">
    <ParamField path="role" type="string" required>
      The role of the message sender. Must be either `"user"` or `"assistant"`.
    </ParamField>

    <ParamField path="content" type="string | array[object]" required>
      The content of the message. Can be a string or array of content blocks.

      **Content Types:**

      * **Text:** `{"type": "text", "text": "..."}`
      * **Image URL:** `{"type": "image_url", "image_url": {"url": "https://..."}}`
      * **Document:** `{"type": "document", "..."}`
      * **String:** Direct string (automatically converted to text block)
    </ParamField>
  </Expandable>
</ParamField>

<ParamField path="max_tokens" type="integer" required>
  Maximum tokens for the response.

  **Range:** `≥ 1`
</ParamField>

<ParamField path="system" type="string | array[object]">
  System prompt/instructions for the model.

  <Expandable title="Format">
    * **String:** Direct system message
    * **Array:** Array of system blocks `[{"type": "text", "text": "..."}]`
  </Expandable>
</ParamField>

<ParamField path="temperature" type="number" default="1.0">
  Controls randomness. Higher = more random, Lower = more deterministic.

  **Range:** `0.0 - 1.0`

  <Expandable title="Example">
    * `0.0` - Completely deterministic
    * `0.7` - Balanced creativity
    * `1.0` - Maximum randomness
  </Expandable>
</ParamField>

<ParamField path="stream" type="boolean" default="false">
  Enable streaming responses (Server-Sent Events format).

  <Expandable title="streaming events">
    * `message_start` - Initial message metadata
    * `content_block_start` - Text block starts
    * `content_block_delta` - Text chunk delta
    * `content_block_stop` - Text block ends
    * `message_delta` - Message metadata update
    * `message_stop` - Stream complete
  </Expandable>
</ParamField>

<ParamField path="top_p" type="number" default="1.0">
  Nucleus sampling - cumulative probability threshold.

  **Range:** `0.0 - 1.0`
</ParamField>

<ParamField path="top_k" type="number">
  Sample from top K tokens by probability.

  **Range:** `> 0`
</ParamField>

<ParamField path="stop_sequences" type="array[string]" default="[]">
  Sequences where generation stops.

  **Max Items:** Typically 5 sequences
</ParamField>

<ParamField path="tools" type="array[object]" default="[]">
  Array of tool/function definitions.

  <Expandable title="tool structure">
    <ParamField path="name" type="string" required>
      The name of the tool/function.
    </ParamField>

    <ParamField path="description" type="string" required>
      A description of what the tool does.
    </ParamField>

    <ParamField path="input_schema" type="object" required>
      JSON Schema defining the tool's input parameters.
    </ParamField>
  </Expandable>

  <Expandable title="Example">
    ```json theme={null}
    "tools": [
      {
        "name": "calculate",
        "description": "Calculate math expression",
        "input_schema": {
          "type": "object",
          "properties": {
            "expression": {"type": "string"}
          },
          "required": ["expression"]
        }
      }
    ]
    ```
  </Expandable>
</ParamField>

<ParamField path="tool_choice" type="string" default="auto">
  How to handle tool selection.

  <Expandable title="options">
    * `"auto"` - Model decides whether to use a tool
    * `"any"` - Model must use a tool
    * `{"type": "tool", "name": "..."}` - Use specific tool
  </Expandable>
</ParamField>

<ParamField path="thinking" type="object">
  Enable extended thinking mode.

  <Expandable title="thinking properties">
    <ParamField path="type" type="string" required>
      Must be `"enabled"` to activate thinking mode.
    </ParamField>

    <ParamField path="budget_tokens" type="integer" required>
      Number of tokens allocated for thinking.

      **Constraints:**

      * Must be `≥ 1024`
      * Must be `< max_tokens`
    </ParamField>
  </Expandable>
</ParamField>

<ParamField path="metadata" type="object" default="{}">
  Custom metadata for tracking/logging.
</ParamField>

<ParamField path="service_tier" type="string" default="auto">
  Which service tier to use.

  <Expandable title="option">
    `"auto"`, `"standard_only"`
  </Expandable>
</ParamField>

## Returns

<ResponseField name="id" type="string">
  The unique identifier for the message.
</ResponseField>

<ResponseField name="type" type="string">
  The type of the response, always `"message"`.
</ResponseField>

<ResponseField name="role" type="string">
  The role of the responder, always `"assistant"`.
</ResponseField>

<ResponseField name="model" type="string">
  The model used for the response.
</ResponseField>

<ResponseField name="stop_reason" type="string">
  The reason generation stopped, e.g., `"end_turn"`.
</ResponseField>

<ResponseField name="stop_sequence" type="string | null">
  The stop sequence that triggered the end, if any.
</ResponseField>

<ResponseField name="content" type="array[object]">
  The generated content.

  <Expandable title="content structure">
    <ResponseField name="type" type="string">
      The type of content block, e.g., `"text"`.
    </ResponseField>

    <ResponseField name="text" type="string">
      The text content.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  Token usage statistics.

  <Expandable title="usage properties">
    <ResponseField name="input_tokens" type="integer">
      Number of input tokens.
    </ResponseField>

    <ResponseField name="output_tokens" type="integer">
      Number of output tokens.
    </ResponseField>

    <ResponseField name="cache_creation_input_tokens" type="integer">
      Cache creation input tokens.
    </ResponseField>

    <ResponseField name="cache_read_input_tokens" type="integer">
      Cache read input tokens.
    </ResponseField>
  </Expandable>
</ResponseField>

## Return Examples

```json Response 200 theme={null}
{
  "id": "msg_01XYZ...",
  "type": "message",
  "role": "assistant",
  "model": "nusantara-base",
  "content": [
    {
      "type": "text",
      "text": "The capital of France is Paris."
    }
  ],
  "stop_reason": "end_turn",
  "usage": {
    "input_tokens": 12,
    "output_tokens": 8
  }
}
```