Inference

​

Fine-tuned models

Our SDK exposes an OpenAI-like interface to chat with your fine-tuned models.

const completion = await montelo.client.chat({
  model: "model-id",
  messages: [],
});

​

OpenAI & Cohere

For OpenAI and Cohere models, simply follow their documentation to learn how to do inference on your fine-tuned models.

• OpenAI docs

• Cohere docs