POST /v1/completions — Swytcho Text Completions API

The /v1/completions endpoint takes a raw text prompt and returns one or more generated continuations. Unlike the chat endpoint, there is no message array or role structure — you supply a prompt string and the model completes it. This format is well-suited for single-turn tasks such as summarization, extraction, code generation, and template-based workflows.

Endpoint

POST https://api.swytcho.com/v1/completions

Request Parameters

string

required

The ID of the model to use. Call GET /v1/models to retrieve the list of models available to your account.

string | array

required

The prompt(s) to complete. Pass a single string for one prompt or an array of strings to batch multiple prompts in a single request.

integer

The maximum number of tokens to generate per completion. Defaults to the model’s context limit. Use this to cap response length and manage costs.

number

Sampling temperature between 0 and 2. Higher values produce more varied output; lower values produce more deterministic output. Defaults to 1. Avoid combining with top_p.

number

Nucleus sampling threshold between 0 and 1. The model samples from the smallest token set whose cumulative probability exceeds this value. Defaults to 1. Avoid combining with temperature.

boolean

When true, the API streams token deltas as server-sent events and sends a final [DONE] message. Defaults to false.

string | array

One or more sequences at which generation stops. Pass a single string or an array of up to four strings.

integer

The number of independent completions to generate for each prompt. Defaults to 1. Note that generating multiple completions increases token usage proportionally.

Request Examples

curl https://api.swytcho.com/v1/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "swytcho-base",
    "prompt": "Summarize the benefits of renewable energy in three bullet points:",
    "max_tokens": 200,
    "temperature": 0.5
  }'

import os
from swytcho import Swytcho

client = Swytcho(api_key=os.environ["SWYTCHO_API_KEY"])

response = client.completions.create(
    model="swytcho-base",
    prompt="Summarize the benefits of renewable energy in three bullet points:",
    max_tokens=200,
    temperature=0.5,
)

print(response.choices[0].text)

import Swytcho from "swytcho";

const client = new Swytcho({ apiKey: process.env.SWYTCHO_API_KEY });

const response = await client.completions.create({
  model: "swytcho-base",
  prompt: "Summarize the benefits of renewable energy in three bullet points:",
  max_tokens: 200,
  temperature: 0.5,
});

console.log(response.choices[0].text);

Response Fields

string

A unique identifier for this completion, prefixed with cmpl-.

string

Always "text_completion".

integer

Unix timestamp (seconds) of when the completion was created.

string

The model ID that was used to generate this response.

array

An array of generated completion objects. Contains one element per prompt per n.

Show Choice object fields

integer

Zero-based index of this choice in the array.

string

The generated text continuation.

string

The reason generation stopped. One of "stop" (natural end or stop sequence hit), "length" (hit max_tokens), or "content_filter" (blocked by safety policy).

object

Token usage statistics for the request.

Show Usage object fields

integer

Number of tokens in the input prompt(s).

integer

Number of tokens across all generated completions.

integer

Total tokens consumed (prompt_tokens + completion_tokens).

Example Response

{
  "id": "cmpl-x9y8z7w6v5u4",
  "object": "text_completion",
  "created": 1717200100,
  "model": "swytcho-base",
  "choices": [
    {
      "index": 0,
      "text": "\n• Reduces greenhouse gas emissions and slows climate change.\n• Lowers long-term energy costs through fuel-free generation.\n• Creates local jobs in manufacturing, installation, and maintenance.",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 17,
    "completion_tokens": 41,
    "total_tokens": 58
  }
}

Overview

Endpoints

POST /v1/completions — Swytcho Text Completions API

Endpoint

Request Parameters

Request Examples

Response Fields

Example Response