—per task?
self-host onlyprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open×4.5—$0 / —Context: 262K → 16K+1
BetterDecider v1.2Open×4.4—$0.02 / —ABetterAutoTrust-JEV-27B v1.1Open×4.4——No image inputSBetterStartLux-Decision v1.1 27BOpen×4.4——vBetterD3 TurboOpen×4.4——Context: 262K → 33KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×4.5—$0 / —Context: 262K → 16K+1Decider v1.2Open×4.4—$0.02 / —AAutoTrust-JEV-27B v1.1Open×4.4——No image inputSStartLux-Decision v1.1 27BOpen×4.4——vD3 TurboOpen×4.4——Context: 262K → 33KRun it yourself
Fits onhardware needs not verified yet
LicenceCC BY-NC 4.0no commercial use
Benchmarks
in Decision modelsFAQ
How much does JPT 0.8B cost?›
There is no per-unit API price: self-host only.
Is JPT 0.8B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is JPT 0.8B, and what is it best at?›
#87 of 99 in Decision models.
Is JPT 0.8B better than tasksource Decider nano v4 (150M)?›
On Community Decision Index 0.4.1, JPT 0.8B scores 15.5 vs 16.4 — about the same.
What is the context window of JPT 0.8B?›
262K tokens.
When was JPT 0.8B released? Is there a newer version?›
Released 2026-09-24. It is the current version in its line.
Is JPT 0.8B open source?›
Yes, the weights are open (cc-by-nc-4.0 licence).
Can I run JPT 0.8B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can JPT 0.8B read images?›
It accepts text and images, video as input.
What is JPT 0.8B?›
JPT 0.8B is an open-weights language model from kirp, released Sep 2026.
What are the best alternatives to JPT 0.8B?›
mammoth-1 (27B) (better).