Octomind Replaces Chat Model Calls with Jev for Binary Decisions

Octomind version 0.54.0 replaced chat model calls for binary agent decisions with the Jev model from TypeSafe AI, which returns only a probability. Responses come in 0.5–1.3 seconds and cost $0.00001–0.0001 per request at $0.042 per million input tokens.

• Jev responds in 70–500 ms and costs $0.042 per 1M input tokens
• In Octomind, model used in five places: skill routing, output evaluation, verifier check, memory, and planning
• Jev can only slow down work but not confirm its completion
• Routing enabled by default on all plans, including free