—per task?
self-host onlyprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open+56%—$0 / —Context: 262K → 16K+1
BetterDecider v1.2Open+54%—$0.02 / —ABetterAutoTrust-JEV-27B v1.1Open+54%——No image inputSBetterStartLux-Decision v1.1 27BOpen+54%——vBetterD3 TurboOpen+53%——Context: 262K → 33KModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+56%—$0 / —Context: 262K → 16K+1Decider v1.2Open+54%—$0.02 / —AAutoTrust-JEV-27B v1.1Open+54%——No image inputSStartLux-Decision v1.1 27BOpen+54%——vD3 TurboOpen+53%——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 9B cost?›
There is no per-unit API price: self-host only.
Is JPT 9B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is JPT 9B, and what is it best at?›
#49 of 99 in Decision models.
Is JPT 9B better than Clef Flash?›
On Community Decision Index 0.4.1, JPT 9B scores 44.1 vs 44.4 — about the same.
What is the context window of JPT 9B?›
262K tokens.
When was JPT 9B released? Is there a newer version?›
Released 2026-09-25. It is the current version in its line.
Is JPT 9B open source?›
Yes, the weights are open (cc-by-nc-4.0 licence).
Can I run JPT 9B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can JPT 9B read images?›
It accepts text and images, video as input.
What is JPT 9B?›
JPT 9B is an open-weights language model from kirp, released Sep 2026.
What are the best alternatives to JPT 9B?›
mammoth-1 (27B) (better).