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

# Completions

> OpenAI-compatible legacy text completion API

## Introduction

Create text completions from a `prompt`, compatible with the OpenAI Completions API. For multi-turn dialogue, prefer [Chat completions](/en/api-reference/endpoint/chat-openai).

## Authentication

<ParamField header="Authorization" type="string" required>
  Bearer Token, e.g. `Bearer sk-xxxxxxxxxx`
</ParamField>

## Request parameters

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

<ParamField body="prompt" type="string | array" required>
  Prompt text (string or array of strings)
</ParamField>

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

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

<ParamField body="stream" type="boolean" default="false">
  Stream response via SSE
</ParamField>

## Request example

```bash theme={null}
curl -X POST "https://api.gravitex.ai/v1/completions" \
  -H "Authorization: Bearer sk-xxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "prompt": "In one sentence, describe AI:",
    "max_tokens": 100,
    "temperature": 0.7
  }'
```

## Common parameters

* **model**: Model ID
* **prompt**: Input prompt
* **max\_tokens**: Cap output length
* **stream**: Set `true` for SSE streaming

See [OpenAI Completions API](https://platform.openai.com/docs/api-reference/completions) for full request/response schemas.