Skip to main content

​
Getting started

This guide gets you from sign-up to your first API call.

​
1. Account setup

  1. Go to llmtune.io and sign up or log in.
  2. Complete account setup in the dashboard.
  3. Add payment method and credits if you plan to run inference or fine-tuning (usage is billed from your balance).

​
2. Create an API key

  1. In the dashboard, open API Keys.
  2. Click Create key and give it a name (e.g. dev or production).
  3. Copy the key. It is shown only once; store it securely (e.g. in a secret manager or env var).
API keys grant full access to your account (inference, training, usage). Do not commit them to source control or expose them in client-side code.

​
3. Base URL

Use this base URL for inference and agent endpoints: 
https://api.llmtune.io
For model-specific inference: 
POST https://api.llmtune.io/v1/models/{modelId}/inference
Replace {modelId} with a supported model ID (e.g. from the models list or dashboard).

​
4. First request

Example: run completion with a single prompt. 
curl https://api.llmtune.io/v1/models/meta-llama/Llama-3.3-70B-Instruct/inference \
  -H "Authorization: Bearer sk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Summarize LLMTune in one sentence.",
    "temperature": 0.6,
    "maxTokens": 200
  }'
Example response: 
{
  "text": "Generated response...",
  "tokens": 42,
  "model": "meta-llama/Llama-3.3-70B-Instruct",
  "latency": 234
}

​
5. Chat completions

For multi-turn chat, use the chat completions endpoint with a messages array: 
curl https://api.llmtune.io/v1/chat/completions \
  -H "Authorization: Bearer sk_live_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/Llama-3.3-70B-Instruct",
    "messages": [
      { "role": "user", "content": "What is 2 + 2?" }
    ],
    "temperature": 0.7,
    "max_tokens": 256
  }'

​
Next steps