Resonatia

Chat Completions

Generate chat completions using quantized language models. Compatible with OpenAI's chat completions format.

Create Chat Completion

Generate a chat completion for the provided messages.

POST
/v1/mesh/chat
OpenAI Compatible
{
  "model": "mesh/llama-3.1-8b-q4",
  "messages": [
    {
      "role": "system",
      "content": "You are a helpful assistant."
    },
    {
      "role": "user",
      "content": "What is quantization in AI models?"
    }
  ],
  "temperature": 0.7,
  "max_tokens": 500,
  "top_p": 1.0,
  "frequency_penalty": 0.0,
  "presence_penalty": 0.0,
  "stream": false
}

OpenAI-Compatible Endpoint

Use /v1/chat/completions for full OpenAI compatibility.

curl https://api.resonatia.io/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mesh/llama-3.1-8b-q4",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'