The problem? Right now, if you want function calling, you're stuck using GPT-4. While it's an amazing model, it's also pretty expensive, which isn't ideal if you're trying to keep costs down. There are a few open-source models out there, but none of them are robust enough for real-world applications.

So, we decided to change that. We've built a new LLM that supports function calling, and we are open-sourcing it. We've benchmarked our model against many other alternatives, and we're confident that it’s the best open-source LLM for function calling. Plus, it’s much cheaper than GPT-4, making it accessible to a wider range of users.

Let us know if you have any questions or feedback. We're excited to see what you build with this new LLM!