Awesome Jev: early projects and use cases
A community-curated list gathers early Jev projects and ideas for developers who already have API access.
Jev Smart Routing: Cut Cost from $18 to $1.30 per 1,000 Calls
User shares using jev as a scorer with Haiku 5.5, Sonnet 5.5, and Opus 5.5 to build a cost-optimized smart model stack. By letting each call climb only as far as the task requires, the cost for 1,000 calls drops from $18.00 (all Opus 5.5) to $1.30.
jev + haiku 5.5 + sonnet 5.5 + opus 5.5 is the cheapest stack that still feels smart 1,000 calls, same napkin: → dump every call on opus 5.5: $18.00 → let each call climb the stack: $1.30 the rule: a call only rises as far as the job forces it your request → jev scores it
· 6 likesOpen on X
More like this
Training an MLP on Qwen 4B to Replicate Jev Behavior
The author shares an open-source project openjev that trains an MLP on qwen 4b to work like Jev, with a Hugging Face link. Link
Swapping an agent's tool-calling reasoning with Jev
The author shares replacing an agent's tool-calling reasoning with Jev, using Fable, Astra, and Opus; early results show drastic savings with very close results, with a demo video promised.
