Featherless AI

featherless.ai · Compute · 1 record · JSON

Featherless AI Compute

paidcardcardDrequest-rate

featherless.ai/pricing · inference API · compute/featherless-ai · JSON · compare

Free tier	no free tier of any kind. Every plan is paid: 'Chat $25/mo', 'Developer from $50/mo', 'Business Custom'. The Chat plan advertises 'Flat-rate pricing designed for scale with unlimited tokens' across a catalogue of '40,000+ open models', capped at a 32K context window and 4 concurrent units. unit unlimited; metered on wall-clock; none
Price	none stated
Per-object cap	not applicable
Retention	not applicable
Egress	not stated
Identity	card not published
Limits	request-rate on the cheapest plan the context window and 4 concurrent units bind before anything else: 32K of context and four units in flight, with no production API on that tier at all. source on the cheapest plan the context window and 4 concurrent units bind before anything else: 32K of context and four units in flight, with no production API on that tier at all.
Binding	request-rate on the cheapest plan the context window and 4 concurrent units bind before anything else: 32K of context and four units in flight, with no production API on that tier at all.
Interface	rest inferred from the tooling the provider documents; not probed
Tooling	not stated
Composes with	USD 25 a month for unlimited interactive chat tokens is the cheapest per-token cost if the workload is one person talking to a model it buys nothing for an agent, because the Chat plan excludes API traffic and automation.
Reliability	no reliability event recorded
Notes	The word 'unlimited' is the trap: the same page's footnote restricts the Chat plan to human-driven use and excludes benchmarking, and the Developer plan is metered per token instead. So the free-looking offer is neither free nor unlimited for a programmatic workload. No free trial is published, which makes this a paid-only record rather than trial-only.
Evidence rung	documented
Checked	2026-10-22 (live); stale on 2026-11-21

Evidence (2)

date	source	what it proved
2026-10-22	featherless.ai/pricing	the plan table's three columns are 'Chat $25/mo', 'Developer from $50/mo', 'Business Custom' with no free column; 'Credits expire: Never'; 'Token volume: Unlimited' on Chat and Business; 'Concurrent units: 4' on Chat, 100 on Developer, quoted
2026-10-22	featherless.ai/	'Flat-rate pricing designed for scale with unlimited tokens'; 'Chat plan is for interactive, human-driven use by the purchaser. Not for reselling, app/API traffic, background automation, or benchmarking', quoted

More fields (1)

{
 "wave2": {
  "class": "paid-inference",
  "free_tier_kind": "none",
  "shape": {
   "vcpu": null,
   "ram_gib": null,
   "gpu_class": null,
   "gpu_count": null
  }
 }
}

Unknown or withheld values (9)

$.egress.metered egress-unknown
$.egress.terms not-stated
$.identity_cost.detail process
$.per_object_cap.notes process
$.per_object_cap.stated not-applicable
$.reliability_note none-observed
$.retention.notes process
$.retention.stated not-applicable
$.tooling not-stated