Endpoints

Completions

Use POST /completions for legacy prompt-in, text-out completions with the OpenAI completions format, parameters and response fields.

Try it in the playground

The legacy completions endpoint takes a raw prompt string and returns generated text, with no chat template applied. It is useful for base models, fill-in-the-middle and older integrations. For new code, use Chat completions.

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

Request

Parameter	Type	Description
`model`	string, required	Model id, e.g. `meta-llama/llama-3.1-8b-instruct`.
`prompt`	string, required	The text to continue.
`max_tokens`	integer	Upper bound on generated tokens.
`temperature`, `top_p`, `top_k`	number	Sampling controls.
`stop`	string \| string[]	Stop sequences.
`seed`	integer	Best-effort deterministic sampling.
`logprobs`	integer	Return log probabilities for the top tokens when the model supports it.
`stream`	boolean	Stream text chunks over SSE.
`provider`, `models`, `transforms`		Same gateway extensions as 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);

Response

{
  "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
  }
}

Errors

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. Errors from the provider are passed through with their original status. See Errors.