Completions

The Completions API allows you to generate text continuations from a prompt. For conversational AI, we recommend using the Chat Completions API instead.

The Chat Completions API is generally preferred for most use cases as it provides better control over the conversation context and system instructions.

The completion model

The completion model takes a text prompt and generates a continuation.

Properties

Name
model
Type
string
Description
The ID of the model to use for completion.
Name
prompt
Type
string
Description
The text prompt to generate a completion for.
Name
max_tokens
Type
integer
Description
The maximum number of tokens to generate.
Name
temperature
Type
number
Description
Controls randomness. Higher values make output more random. Range: 0-2, default: 1.
Name
stream
Type
boolean
Description
If set to true, partial completions will be sent as server-sent events. Default: false.

POST/v1/completions

Create completion

Generate a text completion based on a prompt.

Required attributes

Name
model
Type
string
Description
The model ID to use for completion.
Name
prompt
Type
string
Description
The text prompt to complete.

Optional attributes

Name
max_tokens
Type
integer
Description
Maximum tokens to generate. Default: 16.
Name
temperature
Type
number
Description
Sampling temperature (0-2). Default: 1.
Name
stream
Type
boolean
Description
Enable streaming responses. Default: false.

Request

POST

/v1/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://api.nextbit256.com/v1",
    api_key="your-api-key"
)

response = client.completions.create(
    model="llama3.3:70b",
    prompt="Once upon a time",
    max_tokens=50
)

print(response.choices[0].text)

Response

{
  "id": "cmpl-6ff64705f50d43cbbab7cd03250e9382",
  "object": "text_completion",
  "created": 1742470129,
  "model": "llama3.3:70b",
  "choices": [
    {
      "text": ", in a land far away, there lived a wise old wizard...",
      "index": 0,
      "logprobs": null,
      "finish_reason": "length"
    }
  ],
  "usage": {
    "prompt_tokens": 4,
    "completion_tokens": 50,
    "total_tokens": 54
  }
}