InclusionAI · open weights
Ling 3.0 Flash
InclusionAI’s cost-focused Flash MoE tier for high-frequency hybrid reasoning and agent loops.
- Organisation
- InclusionAI
- Weights published
- Not verified
- Licence
- MIT
- Size
- 124B total / 5.1B active MoE
- Modalities
- text
- Comparison catalog
- Ant Ling 3.0 Flash profile
Practical fit
A budget open-weight option when you need MoE efficiency and can host the expert set.
Deployment note
The exact checkpoint config has 262,144 positions; the vendor describes extension to 1M. Thinking is enabled by default and can be disabled per request. The platform launched the native API July 23; July 24 dates the article, while the exact public weights release day is unverified. Current hosted prices and limits depend on the selected route.
Where to go next
Other open-weight releases
InclusionAI · Publication date not verified
Ant Ling 3.0 Flash VL
MIT (publisher metadata) · 124B total / 5.5B active (MoE)
InclusionAI · Publication date not verified
Ant Ling 3.0 Tiny
MIT (publisher metadata) · 7.9B total / 1.3B active (MoE)
Xiaomi · September 22, 2026
Xiaomi MiMo-V2.6-Pro
MIT · 1.02T total / 42B active MoE