Plans
Explaining how our different subscription tiers work.
Featherless provides serverless access to models, eliminating the need to manage infrastructure.
Our plans are subscription and concurrency based. Allowing unlimited monthly requests with a fixed number of concurrent requests. A paid subscription is able to access all models up to a given size.
Featherless offers two consumer plans:
Featherless Basic ($10/month):
Use any model up to 15B parameters
2 concurrent connections (no other restrictions on tokens or requests)
Featherless Premium ($25/month)
Access any model in the catalogue (including Deepseek R1 and V3)
Up to 4 concurrent connections (depending on model size - more for smaller models)
And one scalable business plan:
Featherless Scale ($75 per scale unit/month):
All the benefits of Featherless Premium
Per unit 2x Premium models or 6x Basic models
Run your own private models from Hugging Face*
model must be one of the compatible architectures.
For more info on how the concurrency limits work visit:
Concurrency Limits
Explaining how subscription tiers translate to concurrent inference call maximums.