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

# Completions

> Create a legacy text completion through the attested Confidential AI gateway.

<Warning>
  This endpoint is legacy. Use [Chat Completions](/phala-cloud/confidential-ai/confidential-model/api-reference/chat-completions) or [Responses](/phala-cloud/confidential-ai/confidential-model/api-reference/responses) for new applications.
</Warning>

## Endpoint

```bash theme={"system"}
POST https://inference.phala.com/v1/completions
```

## Request

```json theme={"system"}
{
  "model": "gpt-3.5-turbo-instruct",
  "prompt": "Say this is a test",
  "max_tokens": 7,
  "temperature": 0
}
```

## Response

```json theme={"system"}
{
  "id": "cmpl-123",
  "object": "text_completion",
  "created": 1677652288,
  "model": "gpt-3.5-turbo-instruct",
  "choices": [
    {
      "text": "\n\nThis is a test.",
      "index": 0,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 5,
    "completion_tokens": 7,
    "total_tokens": 12
  }
}
```

Like other inference endpoints, raw HTTP responses include `x-receipt-id` for verification.

## Related

<CardGroup cols={2}>
  <Card title="Chat Completions" icon="comments" href="/phala-cloud/confidential-ai/confidential-model/api-reference/chat-completions" />

  <Card title="Get Receipt" icon="receipt" href="/phala-cloud/confidential-ai/confidential-model/api-reference/receipts" />
</CardGroup>