> Across all attempted problems, the agents sent 4.9 million messages and used about 300 billion output tokens
Don't even try to do the math on how much that would cost at normal API prices. And we don't even know how much more expensive this internal-only model would be!
300e9 output tokens at the current Astra per-token API pricing ($50 per 1e6 output tokens) would be roughly $15,000,000 ignoring input tokens.
Napkin math if we assume gpt 6 astra on max is >$15 million (just for output tokens) for those wondering.