Access 2 Jon Durbin models through the OpenRouter unified API including Bagel 34B v0.2 and Airoboros 70B. Compare pricing, context windows, benchmarks, and capabilities between different Jon Durbin models.
Jon Durbin tokens processed on OpenRouter
An experimental fine-tune of [Yi 34b 200k](/models/01-ai/yi-34b-200k) using [bagel](https://github.com/jondurbin/bagel). This is the version of the fine-tune before direct preference optimization (DPO) has been applied. DPO performs better on benchmarks, but this version is likely better for creative writing, roleplay, etc.
A Llama 2 70B fine-tune using synthetic data (the Airoboros dataset). Currently based on [jondurbin/airoboros-l2-70b](https://huggingface.co/jondurbin/airoboros-l2-70b-2.2.1), but might get updated in the future.