Endpoint

Completions (legacy)

Endpoint completions legacy menerima string prompt mentah dan mengembalikan teks hasil generasi, cocok untuk model dasar dan integrasi lama.

Coba di playground

Endpoint completions legacy menerima string prompt mentah dan mengembalikan teks hasil generasi, tanpa template chat. Endpoint ini berguna untuk model dasar, fill-in-the-middle, dan integrasi lama. Untuk kode baru, gunakan Chat completions.

POST https://api14.com/api/v1/completions
Authorization: Bearer sk-api14-...
Content-Type: application/json

Request

Parameter	Tipe	Deskripsi
`model`	string, wajib	ID model, mis. `meta-llama/llama-3.1-8b-instruct`.
`prompt`	string, wajib	Teks yang akan dilanjutkan.
`max_tokens`	integer	Batas atas jumlah token yang dihasilkan.
`temperature`, `top_p`, `top_k`	number	Pengaturan sampling.
`stop`	string \| string[]	Stop sequence.
`seed`	integer	Sampling deterministik dengan upaya terbaik.
`logprobs`	integer	Mengembalikan log probabilitas untuk token teratas jika model mendukungnya.
`stream`	boolean	Stream potongan teks lewat SSE.
`provider`, `models`, `transforms`		Ekstensi gateway yang sama seperti pada chat completions.

curl https://api14.com/api/v1/completions \
  -H "Authorization: Bearer $API14_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-3.5-turbo-instruct",
    "prompt": "The three primary colors are",
    "max_tokens": 20
  }'

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api14.com/api/v1",
  apiKey: process.env.API14_API_KEY,
});

const result = await client.chat.completions.create({
  "model": "openai/gpt-5-mini",
  "messages": [
    {
      "role": "user",
      "content": "Explain vector databases in two sentences."
    }
  ]
});
console.log(result.choices[0].message.content);

Respons

{
  "id": "gen-1760000000-xyz789",
  "object": "text_completion",
  "created": 1760000000,
  "model": "openai/gpt-3.5-turbo-instruct",
  "choices": [
    { "index": 0, "text": " red, yellow and blue.", "finish_reason": "stop" }
  ],
  "usage": {
    "prompt_tokens": 6,
    "completion_tokens": 7,
    "total_tokens": 13,
    "cost": 0.0000195
  }
}

Error

400 model_required, 400 invalid_json, 401 invalid_api_key, 402 insufficient_balance, 403 model_not_allowed / plan_required, 404 model_not_found, 413 payload_too_large, 429 rate_limited, 502 upstream_unavailable. Error dari provider diteruskan dengan status aslinya. Lihat Error.