@Mnilax wired Jev into the routing layer of a build that had been running on Astra and says the same task finished 37 minutes sooner with no malformed responses to retry. The post also cites TypeSafe’s published figures: $0.042 per million input tokens with free output, 67.8% matching Sonnet 5 on their eval at 294x less cost and 195x the speed, 0.114s versus 8.566s for GPT-5.6 Terra on the same demo, and about 10 decisions per second in the Doom demo.

Mnimiy (@Mnilax) published this on 2026-09-16. @Mnilax wired Jev into the routing layer of a build that had been running on Astra and says the same task finished 37 minutes sooner with no malformed responses to retry. The post also cites TypeSafe’s published figures: $0.042 per million input tokens with free output, 67.8% matching Sonnet 5 on their eval at 294x less cost and 195x the speed, 0.114s versus 8.566s for GPT-5.6 Terra on the same demo, and about 10 decisions per second in the Doom demo. man who co-invented ChatGPT just shipped a model that does in 0.114 sec what GPT Astra does in 8.5. How Jev or TypeSafe is used, in the post's own words: “i wired Jev into the routing layer of a build i was running on Astra: same task finished 37 MIN SOONER, zero malformed responses to retry.” The post does not name a separate audience. It is for people reading what @Mnilax shows here (it quotes @CompleteSkeptic; it includes media).