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

# Completions

> Create text completions (legacy endpoint)

## Overview

<Warning>
  This is a legacy endpoint. We recommend using [Chat Completions](/api-reference/chat-completions) for all use cases.
</Warning>

Create a text completion with the specified model.

## Request

### Body Parameters

<ParamField body="model" type="string" required>
  Model ID to use
</ParamField>

<ParamField body="prompt" type="string or array" required>
  The prompt(s) to generate completions for
</ParamField>

<ParamField body="max_tokens" type="integer" default="16">
  Maximum tokens to generate
</ParamField>

<ParamField body="temperature" type="number" default="1">
  Sampling temperature
</ParamField>

<ParamField body="stream" type="boolean" default="false">
  Whether to stream responses
</ParamField>

## Example

```bash theme={null}
curl https://api.savegate.ai/v1/completions \
  -H "Authorization: Bearer sk-savegate-xxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-3.5-turbo-instruct",
    "prompt": "Say this is a test",
    "max_tokens": 7,
    "temperature": 0
  }'
```

<Note>
  For new applications, use the Chat Completions endpoint instead.
</Note>