—per task?
self-host onlyprice
—output speed?
262Kcontext
Alternatives?
ModelScoreCostPer taskWhat changes
bBettermammoth-1 (27B)Open+27%—$0 / —Context: 262K → 16K+2bOpenelephant-1 (9B)+11%—$0 / —Context: 262K → 16K+2
BetterDecider v1.2Open+25%—$0.02 / —Memory (4-bit): 4.9 GB → 15 GBABetterAutoTrust-JEV-27B v1.1Open+25%——Memory (4-bit): 4.9 GB → 16 GB+1SBetterStartLux-Decision v1.1 27BOpen+25%——Memory (4-bit): 4.9 GB → 16 GBModelScoreCostPer taskWhat changes
Nothing here yet.
ModelScoreCostPer taskWhat changes
bmammoth-1 (27B)Open+27%—$0 / —Context: 262K → 16K+2Decider v1.2Open+25%—$0.02 / —Memory (4-bit): 4.9 GB → 15 GBAAutoTrust-JEV-27B v1.1Open+25%——Memory (4-bit): 4.9 GB → 16 GB+1SStartLux-Decision v1.1 27BOpen+25%——Memory (4-bit): 4.9 GB → 16 GBvD3 TurboOpen+24%——Context: 262K → 33K+1ModelScoreCostPer taskWhat changes
belephant-1 (9B)Open+11%—$0 / —Context: 262K → 16K+2Decider Flash v1.2Opensame—$0.01 / —OOneJev1.6 9BOpen-2%——Memory (4-bit): 4.9 GB → 5.5 GBFfrontier-infra Jebadiah 9B v2.1 (t1e)Open-6%——Memory (4-bit): 4.9 GB → 5.7 GBvD3 MiniOpen-8%——ModelScoreCostPer taskWhat changes
vD3 TurboOpen+24%——Context: 262K → 33K+1vD3Open+24%——Memory (4-bit): 4.9 GB → 15 GBvD3 MiniOpen-8%——vvLLM-SR Decision 2.0 Lux 9BOpen-15%——Context: 262K → 16K+2vvLLM-SR Decision 2.0 Nox 4BOpen-25%——Context: 262K → 16K+2vvLLM-SR d3-nano (2B)Open-37%——vvLLM-SR d3-lite (0.8B)Open-52%——vvLLM-SR Decision 2.0 Sol 2BOpen-56%——Context: 262K → 16K+2All vLLM Semantic Router models →Run it yourself
estimateFits on✓ 8 GB (phone, laptop) · compressed✓ 16 GB · 8-bit✓ 24 GB GPU · full quality✓ 48 GB GPU · full quality✓ 80 GB GPU · full quality
LicenceApache-2.0free for commercial use
Benchmarks
in Decision modelsFAQ
How much does D3 Flash cost?›
There is no per-unit API price: self-host only.
Is D3 Flash free to use?›
There is no free API. The weights are open, so you can run it yourself.
How good is D3 Flash, and what is it best at?›
#33 of 99 in Decision models.
Is D3 Flash better than Decider Flash v1.2?›
On Community Decision Index 0.4.1, D3 Flash scores 54.3 vs 54.3 — about the same.
What is the context window of D3 Flash?›
262K tokens.
When was D3 Flash released? Is there a newer version?›
Released 2026-10-10. It is the current version in its line.
Is D3 Flash open source?›
Yes, the weights are open (Apache-2.0 licence).
Can I run D3 Flash locally?›
The weights are open and can be self-hosted; hardware needs are not confirmed yet.
Can D3 Flash read images?›
It accepts text and images, video as input.
What is D3 Flash?›
D3 Flash is an open-weights language model from vLLM Semantic Router, released Oct 2026.
What are the best alternatives to D3 Flash?›
mammoth-1 (27B) (better), elephant-1 (9B) (open weights).