—per task?
price not verifiedprice
—output speed?
33Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open×3.3—$0 / —Context: 33K → 16K
BetterDecider v1.2Open×3.3—$0.02 / —ABetterAutoTrust-JEV-27B v1.1Open×3.3——SBetterStartLux-Decision v1.1 27BOpen×3.3——vBetterD3 TurboOpen×3.2——ModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×3.3—$0 / —Context: 33K → 16KDecider v1.2Open×3.3—$0.02 / —AAutoTrust-JEV-27B v1.1Open×3.3——SStartLux-Decision v1.1 27BOpen×3.3——vD3 TurboOpen×3.2——ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open×3.3—$0 / —Context: 33K → 16KDecider v1.2Open×3.3—$0.02 / —AAutoTrust-JEV-27B v1.1Open×3.3——SStartLux-Decision v1.1 27BOpen×3.3——vD3 TurboOpen×3.2——ModelScoreCostPer taskWhat changes
SSieve 27B v2Open×2.9——Context: 33K → 16KSSieve 2B v3Open+65%——Context: 33K → 16KAll Sthānika AI models →Run it yourself
Fits onhardware needs not verified yet
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does Sieve 0.8B cost?›
There is no per-unit API price: price not verified.
How good is Sieve 0.8B, and what is it best at?›
#80 of 99 in Decision models.
Is Sieve 0.8B better than Intern Decision 2B?›
On Community Decision Index 0.4.1, Sieve 0.8B scores 20.8 vs 20.9 — about the same.
What is the context window of Sieve 0.8B?›
33K tokens.
When was Sieve 0.8B released? Is there a newer version?›
Released 2026-10-12. It is the current version in its line.
Is Sieve 0.8B open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run Sieve 0.8B locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can Sieve 0.8B read images?›
No, it accepts text only.
What is Sieve 0.8B?›
Sieve 0.8B is an open-weights language model from Sthānika AI, released Oct 2026.
What are the best alternatives to Sieve 0.8B?›
mammoth-1 (27B) (better).