curl --request POST \
  --url https://api.fastrun.si/v1/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "google/gemma-4-31b-it",
  "prompt": "The three primary colors are",
  "max_tokens": 32
}
'

import requests

url = "https://api.fastrun.si/v1/completions"

payload = {
    "model": "google/gemma-4-31b-it",
    "prompt": "The three primary colors are",
    "max_tokens": 32
}
headers = {
    "Authorization": "Bearer <token>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {Authorization: 'Bearer <token>', 'Content-Type': 'application/json'},
  body: JSON.stringify({
    model: 'google/gemma-4-31b-it',
    prompt: 'The three primary colors are',
    max_tokens: 32
  })
};

fetch('https://api.fastrun.si/v1/completions', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

{
  "id": "<string>",
  "object": "text_completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "text": "<string>",
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 123,
    "completion_tokens": 123,
    "total_tokens": 123,
    "prompt_tokens_details": {
      "cached_tokens": 123
    }
  }
}

{
  "error": {
    "message": "model is required",
    "type": "invalid_request_error",
    "code": 400
  }
}

{
  "error": {
    "message": "invalid or missing API key",
    "type": "authentication_error",
    "code": 401
  }
}

{
  "error": {
    "message": "all backends for this model are at capacity",
    "type": "rate_limit_error",
    "code": 429
  }
}

{
  "error": {
    "message": "all backends refused the request",
    "type": "upstream_error",
    "code": 502
  }
}

{
  "error": {
    "message": "no backend is available for this model",
    "type": "unavailable",
    "code": 503
  }
}