Featherless Plans Pricing
Featherless AI uses flat monthly subscription pricing with unlimited tokens rather than per-token billing. Each tier sets a fixed number of concurrent connections plus limits on model size and context length; smaller models allow higher effective throughput than larger ones. Consumer plans run from Feather Basic to Feather Premium and agent tiers; business plans are sold per unit with private model deployment available at the top end.
Featherless Plans Pricing is the machine-readable pricing-plan profile for Featherless AI on the APIs.io network, conforming to the API Commons Plans specification.
It defines 4 plans, covering flat tiers, with named plans including Feather Basic, Feather Premium, Feather 229B Full Context, Feather Max.
Tagged areas include AI, LLM, Inference, Serverless, and Open Models.
Plans
Entry hobby tier with unlimited tokens, access to any model up to 15B parameters, and 2 concurrent connections.
- Chat Completions
- Completions
- Embeddings
- Models (up to 15B)
Dev/testing tier with unlimited tokens, access to any model in the catalogue regardless of size, and 4 concurrent connections.
- Chat Completions
- Completions
- Embeddings
- Models (any size)
Agent/business tier with models up to 229B parameters, context up to 256K, and 8 concurrent connections per unit.
- Chat Completions
- Completions
- Models (up to 229B)
- Context up to 256K
Top business tier with full catalogue access at any model size, context up to 256K, and 8 concurrent connections per unit; supports private model deployment.
- Chat Completions
- Completions
- Models (any size)
- Context up to 256K
- Private Model Deployment