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

# Chat completions

> Send a text generation request to Kyara Intelligence. Supports streaming over Server-Sent Events and the standard OpenAI sampling parameters.

The chat completions endpoint takes standard OpenAI-format requests and returns text. Point any OpenAI-compatible client at the Kyara base URL to use it. The endpoint is text-only. See [Unsupported Features](/reference/unsupported-features) for the capabilities, such as tool calling, that are not available.

## Request

```
POST https://api.kyara-intelligence.com/v1/chat/completions
```

<CodeGroup>
  ```bash curl theme={null}
  curl https://api.kyara-intelligence.com/v1/chat/completions \
    -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "deepseek/deepseek-v4-flash",
      "messages": [
        { "role": "user", "content": "Hello!" }
      ]
    }'
  ```

  ```javascript JavaScript theme={null}
  import OpenAI from "openai";

  const client = new OpenAI({
    baseURL: "https://api.kyara-intelligence.com/v1",
    apiKey: process.env.KYARA_INTELLIGENCE_API_KEY,
  });

  const response = await client.chat.completions.create({
    model: "deepseek/deepseek-v4-flash",
    messages: [{ role: "user", content: "Hello!" }],
  });

  console.log(response.choices[0].message.content);
  ```

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

  client = OpenAI(
      base_url="https://api.kyara-intelligence.com/v1",
      api_key=os.environ.get("KYARA_INTELLIGENCE_API_KEY"),
  )

  response = client.chat.completions.create(
      model="deepseek/deepseek-v4-flash",
      messages=[{"role": "user", "content": "Hello!"}],
  )

  print(response.choices[0].message.content)
  ```
</CodeGroup>

<ParamField body="model" type="string" required>
  The model ID to use for the request. Find available model IDs in the [catalog](https://kyara-intelligence.com/models).
</ParamField>

<ParamField body="messages" type="array" required>
  An array of message objects forming the conversation. Each object requires a `role` (`system`, `developer`, `user`, or `assistant`) and a `content` string. Content must be plain text. Multimodal arrays are rejected.
</ParamField>

<ParamField body="temperature" type="number">
  Sampling temperature between `0` and `2`. Higher values produce more varied output; lower values produce more focused, deterministic output. Support varies per model.
</ParamField>

<ParamField body="top_p" type="number">
  Nucleus sampling probability mass. The model considers only the tokens comprising the top `top_p` probability mass. Support varies per model.
</ParamField>

<ParamField body="top_k" type="integer">
  Kyara extension. Limits sampling to the top `k` most likely tokens. Accepted by many models beyond the OpenAI standard.
</ParamField>

<ParamField body="max_tokens" type="integer">
  Maximum number of tokens to generate. You can use `max_completion_tokens` interchangeably.
</ParamField>

<ParamField body="max_completion_tokens" type="integer">
  Alias for `max_tokens`. Maximum number of tokens to generate in the completion.
</ParamField>

<ParamField body="stream" type="boolean">
  Set to `true` to receive the response as Server-Sent Events, token by token. Defaults to `false`.
</ParamField>

<ParamField body="reasoning" type="object">
  Controls reasoning behaviour for models that support it. Pass an object with either or both of:

  * `effort` (string), for example `"low"`, `"medium"`, or `"high"`
  * `max_tokens` (integer), the maximum tokens to spend on reasoning

  The top-level `reasoning_effort` is also accepted and is folded into `reasoning.effort`. If you set both, `reasoning.effort` takes precedence.
</ParamField>

<ParamField body="n" type="integer">
  Number of completion choices to generate. Only `1` is supported; any other value returns a `400` error. Defaults to `1`.
</ParamField>

<ParamField body="stop" type="string | array">
  Up to four sequences where the model will stop generating further tokens.
</ParamField>

<ParamField body="seed" type="integer">
  A seed for deterministic sampling. Passing the same seed and request parameters should produce the same result, though determinism is not guaranteed.
</ParamField>

## Response

A successful request returns a JSON object matching the OpenAI chat completions schema.

```json theme={null}
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "model": "deepseek/deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "Hello! How can I help you today?" },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 9, "completion_tokens": 9, "total_tokens": 18 }
}
```

<ResponseField name="id" type="string">
  A unique identifier for the completion, prefixed with `chatcmpl-`.
</ResponseField>

<ResponseField name="object" type="string">
  Always `"chat.completion"` for non-streaming responses.
</ResponseField>

<ResponseField name="model" type="string">
  The model ID that was used to generate the response.
</ResponseField>

<ResponseField name="choices" type="array">
  An array of completion choices.

  <Expandable title="Choice object">
    <ResponseField name="index" type="integer">
      Zero-based index of this choice in the array.
    </ResponseField>

    <ResponseField name="message" type="object">
      The generated message. Contains `role` (`"assistant"`) and `content` (string).
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      The reason generation stopped. Common values: `"stop"`, `"length"`.
    </ResponseField>
  </Expandable>
</ResponseField>

<ResponseField name="usage" type="object">
  Token usage for the request.

  <Expandable title="Usage object">
    <ResponseField name="prompt_tokens" type="integer">
      Number of tokens in the input messages.
    </ResponseField>

    <ResponseField name="completion_tokens" type="integer">
      Number of tokens in the generated output.
    </ResponseField>

    <ResponseField name="total_tokens" type="integer">
      Total tokens consumed (`prompt_tokens` + `completion_tokens`).
    </ResponseField>
  </Expandable>
</ResponseField>

## Streaming

Set `"stream": true` to receive the response as Server-Sent Events. Kyara sends one `data:` event per token and terminates the stream with `data: [DONE]`.

```bash curl theme={null}
curl https://api.kyara-intelligence.com/v1/chat/completions \
  -H "Authorization: Bearer $KYARA_INTELLIGENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4-flash",
    "stream": true,
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'
```

To include token usage in the final stream event, add `"stream_options": { "include_usage": true }` to your request.

<Note>
  Model IDs and pricing can change during early access. Use the [models page](https://kyara-intelligence.com/models) as the current source of truth for available models.
</Note>

<Note>
  Features such as tool calling, structured outputs, vision, and embeddings are not supported. See [Unsupported Features](/reference/unsupported-features) for the complete list.
</Note>