—per task?
self-host onlyprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open×5.4—$0 / —Context: 262K → 16K+1ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×5.4—$0 / —Context: 262K → 16K+1ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×5.4—$0 / —Context: 262K → 16K+1ModelScoreCostPer taskWhat changes
SIntern Decision 4BOpen×3——SIntern Decision 2BOpen+65%——All Shanghai AI Lab (InternLM) models →Run it yourself
Fits onhardware needs not verified yet
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does Intern Decision 0.8B cost?›
There is no per-unit API price: self-host only.
Is Intern Decision 0.8B free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is Intern Decision 0.8B, and what is it best at?›
#88 of 99 in Decision models.
Is Intern Decision 0.8B better than JPT 0.8B?›
On Community Decision Index 0.4.1, Intern Decision 0.8B scores 12.7 vs 15.5 — lower.
What is the context window of Intern Decision 0.8B?›
262K tokens.
When was Intern Decision 0.8B released? Is there a newer version?›
Released 2026-09-26. It is the current version in its line.
Is Intern Decision 0.8B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Intern Decision 0.8B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Intern Decision 0.8B read images?›
It accepts text and images, video as input.
What is Intern Decision 0.8B?›
Intern Decision 0.8B is an open-weights language model from Shanghai AI Lab (InternLM), released Sep 2026.
What are the best alternatives to Intern Decision 0.8B?›
mammoth-1 (27B) (better).