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

# Chat Completions

> POST /v1/chat/completions — Create a compressed chat completion.

## Endpoint

```
POST https://www.opencompress.ai/api/v1/chat/completions
```

## Headers

| Header          | Required | Description                   |
| --------------- | -------- | ----------------------------- |
| `Authorization` | Yes      | `Bearer sk-occ-your-key-here` |
| `Content-Type`  | Yes      | `application/json`            |

## Request body

<ParamField body="model" type="string" required>
  Model identifier. See [Supported Models](/features/supported-models) for the full list.

  Examples: `gpt-4o`, `claude-sonnet-4-6`, `gemini-2.5-pro`
</ParamField>

<ParamField body="messages" type="array" required>
  Array of message objects. Each message has a `role` and `content`.

  Supported roles: `system`, `user`, `assistant`
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  If `true`, returns a stream of server-sent events.
</ParamField>

<ParamField body="temperature" type="number">
  Sampling temperature (0-2). Passed through to the model.
</ParamField>

<ParamField body="max_tokens" type="integer">
  Maximum tokens to generate. Passed through to the model.
</ParamField>

<ParamField body="top_p" type="number">
  Nucleus sampling parameter. Passed through to the model.
</ParamField>

<ParamField body="stop" type="string | array">
  Stop sequences. Passed through to the model.
</ParamField>

All standard OpenAI parameters (`frequency_penalty`, `presence_penalty`, `logprobs`, `tools`, `tool_choice`, etc.) are passed through to the upstream model.

## Response

<ResponseField name="id" type="string">
  Unique identifier for this completion.
</ResponseField>

<ResponseField name="object" type="string">
  Always `"chat.completion"`.
</ResponseField>

<ResponseField name="created" type="integer">
  Unix timestamp of when the completion was created.
</ResponseField>

<ResponseField name="model" type="string">
  The model used, matching your request.
</ResponseField>

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

  <Expandable title="Choice object">
    <ResponseField name="index" type="integer">
      Index of this choice.
    </ResponseField>

    <ResponseField name="message" type="object">
      The assistant's message with `role` and `content`.
    </ResponseField>

    <ResponseField name="finish_reason" type="string">
      Why generation stopped: `"stop"`, `"length"`, `"tool_calls"`.
    </ResponseField>
  </Expandable>
</ResponseField>

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

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

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

    <ResponseField name="total_tokens" type="integer">
      Total tokens (prompt + completion).
    </ResponseField>
  </Expandable>
</ResponseField>

## Example

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

  client = OpenAI(
      base_url="https://www.opencompress.ai/api/v1",
      api_key="sk-occ-your-key-here",
  )

  response = client.chat.completions.create(
      model="gpt-4o",
      messages=[
          {"role": "system", "content": "You are a concise technical writer."},
          {"role": "user", "content": "Explain how JWT authentication works."},
      ],
      temperature=0.7,
      max_tokens=500,
  )

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

  ```bash cURL theme={null}
  curl https://www.opencompress.ai/api/v1/chat/completions \
    -H "Authorization: Bearer sk-occ-your-key-here" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-4o",
      "messages": [
        {"role": "system", "content": "You are a concise technical writer."},
        {"role": "user", "content": "Explain how JWT authentication works."}
      ],
      "temperature": 0.7,
      "max_tokens": 500
    }'
  ```
</CodeGroup>