curl --request POST \
  --url https://api.fastrun.si/v1/chat/completions \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "google/gemma-4-31b-it",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Explain prefix caching in one sentence."
    }
  ],
  "max_tokens": 200
}
'

import requests

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

payload = {
    "model": "google/gemma-4-31b-it",
    "messages": [
        {
            "role": "system",
            "content": "You are a concise assistant."
        },
        {
            "role": "user",
            "content": "Explain prefix caching in one sentence."
        }
    ],
    "max_tokens": 200
}
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',
    messages: [
      {role: 'system', content: 'You are a concise assistant.'},
      {role: 'user', content: 'Explain prefix caching in one sentence.'}
    ],
    max_tokens: 200
  })
};

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

{
  "id": "<string>",
  "object": "chat.completion",
  "created": 123,
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {
        "role": "assistant",
        "content": "<string>",
        "reasoning": "<string>",
        "tool_calls": [
          {
            "id": "<string>",
            "type": "function",
            "function": {
              "name": "<string>",
              "arguments": "<string>"
            }
          }
        ]
      },
      "finish_reason": "stop",
      "logprobs": {}
    }
  ],
  "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
  }
}