Interestingly, I've seen better performance and similar cost to whats on JevBench
Plus, a lot of IP from a previous startup (that was acquired last year), Pi Labs, was used to help push the model to SOTA performance quickly. The startup was building scoring models long before Jev released
Actually, it is price competitive! As of now, $0.042/1M input tokens - the same as Jev as far as I'm aware. Checkout the blog. https://techcommunity.microsoft.com/blog/azure-ai-foundry-bl...
Docs are up now here: https://learn.microsoft.com/en-us/azure/foundry/foundry-mode...
Interestingly, I've seen better performance and similar cost to whats on JevBench
Plus, a lot of IP from a previous startup (that was acquired last year), Pi Labs, was used to help push the model to SOTA performance quickly. The startup was building scoring models long before Jev released
Actually, it is price competitive! As of now, $0.042/1M input tokens - the same as Jev as far as I'm aware. Checkout the blog. https://techcommunity.microsoft.com/blog/azure-ai-foundry-bl...
Docs are up now here: https://learn.microsoft.com/en-us/azure/foundry/foundry-mode...