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

# Create Completion

> Generate text completions using the specified model.

<RequestExample>
  ```bash cURL theme={null}
  curl https://gateway.bud.studio/v1/completions \
    -H "Authorization: Bearer YOUR_API_KEY" \
    -H "Content-Type: application/json" \
    -d '{
      "model": "gpt-3.5-turbo-instruct",
      "prompt": "Write a tagline for an ice cream shop.",
      "max_tokens": 50,
      "temperature": 0.7
    }'
  ```
</RequestExample>

<ResponseExample>
  ```json 200 theme={null}
  {
    "id": "cmpl-abc123",
    "object": "text_completion",
    "created": 1699000000,
    "model": "gpt-3.5-turbo-instruct",
    "choices": [
      {
        "text": "\n\nSweet moments, one scoop at a time.",
        "index": 0,
        "logprobs": null,
        "finish_reason": "stop"
      }
    ],
    "usage": {
      "prompt_tokens": 10,
      "completion_tokens": 12,
      "total_tokens": 22
    }
  }
  ```
</ResponseExample>

## Headers

| Parameter     | Type   | Required | Description                  |
| ------------- | ------ | -------- | ---------------------------- |
| Authorization | string | Yes      | Bearer authentication header |

## Body

| Parameter           | Type            | Required | Description                                                            |
| ------------------- | --------------- | -------- | ---------------------------------------------------------------------- |
| model               | string          | Yes      | Model identifier to use for completion                                 |
| prompt              | string or array | Yes      | Text prompt(s) to complete. Can be a single string or array of strings |
| suffix              | string          | No       | Text to append after completion for insert mode                        |
| max\_tokens         | integer         | No       | Maximum tokens to generate. Default: 16                                |
| temperature         | float           | No       | Sampling temperature (0.0 to 2.0). Default: 1.0                        |
| top\_p              | float           | No       | Nucleus sampling parameter. Default: 1.0                               |
| n                   | integer         | No       | Number of completions to generate. Default: 1                          |
| stream              | boolean         | No       | Enable streaming response. Default: false                              |
| logprobs            | integer         | No       | Include log probabilities on the most likely tokens                    |
| echo                | boolean         | No       | Echo back the prompt in addition to completion. Default: false         |
| stop                | string or array | No       | Sequences where the API will stop generating                           |
| presence\_penalty   | float           | No       | Penalize new tokens based on presence (-2.0 to 2.0). Default: 0        |
| frequency\_penalty  | float           | No       | Penalize new tokens based on frequency (-2.0 to 2.0). Default: 0       |
| repetition\_penalty | float           | No       | Penalize token repetition. Default: 1.0                                |
| best\_of            | integer         | No       | Generate n completions server-side and return the best                 |
| logit\_bias         | object          | No       | Modify likelihood of specified tokens                                  |
| user                | string          | No       | Unique identifier representing your end-user                           |
| seed                | integer         | No       | Random seed for deterministic sampling                                 |
| ignore\_eos         | boolean         | No       | Continue generating until max\_tokens is reached. Default: false       |

## Supported Providers

<CardGroup cols={4}>
  <Card title="OpenAI" icon="openai">
    GPT-3.5 Turbo Instruct for legacy completions
  </Card>

  <Card title="Azure OpenAI" icon="microsoft">
    Enterprise completions deployments
  </Card>

  <Card title="Together AI" icon="arrow-progress">
    Llama, Mixtral, and open-source models
  </Card>

  <Card title="Fireworks" icon="fire">
    Fast completions for various LLMs
  </Card>
</CardGroup>