Featherless
Serverless API access to thousands of open-weight AI models
Linked from featherless.ai · checked 29 Oct
- Tool type
- Serverless open-model inference API
- Made for
- Developers and roleplay/chat users
- Runs on
- Hosted API with web dashboard
- Models run on Featherless serverless infrastructure and dedicated GPUs on business plans; access is through an API endpoint and the web account.
What it does
Featherless takes text prompts and API requests sent to an OpenAI-compatible endpoint and returns model-generated text completions and chat responses. Its catalogue spans many open-weight model families, including Qwen, Llama, Mistral, DeepSeek, and RWKV, and the pages describe support for tool calling, vision, embeddings, and speech models.
People use it by generating an API key and pointing an application, agent framework, or chat frontend such as SillyTavern or RisuAI at the endpoint. The distinct feature is access to a large open-model library through one key, with plan choices separating flat-rate chat use from per-token developer credits and dedicated GPU business deployments.
It suits developers building agents or apps, and roleplay users who want chat access to many models. Access requires signing up and buying a subscription or credit balance. Chat plans prohibit app or API traffic and background automation, and the plan context window and concurrency limits constrain heavier workloads.
What it can do
- Serverless inference over an OpenAI-compatible API for open-weight models
- Access to a catalogue of 40,000+ models through a single API key
- Tool calling support
- Vision and multimodal model access
- Embeddings and classifier endpoints
- Speech and audio endpoints for TTS models
Works with
- SillyTavern
- RisuAI
- Wyvern
- Cline
- Kilo Code
- OpenCode
- OpenHands
- n8n
Before you choose
- Chat plan is for human-driven interactive use only and excludes app/API traffic, reselling, and background automation.
- Developer plan credits are billed per token at each model's own rate, with input and output priced separately per million tokens.
- Business plan requires contacting sales with annual contracts and volume pricing.
Listed under
Get started
Create an account to get an API key; a subscription or credit balance is needed for paid access.
- Create an account at featherless.ai/register
- Choose a plan and add credits or subscribe
- Generate an API key and point an OpenAI-compatible client at the Featherless endpoint
Plans and prices
Prices in USDDeveloper credits draw down per successful request at each model's per-token rate; unused credits do not expire. Chat plan renews monthly and excludes API traffic. Business pricing requires talking to sales.
- Unlimited tokens for interactive use
- 32K context
- Up to 256K context
- Usage-based credits
- Dedicated GPUs
- Named engineers and SLA
Source: featherless.ai/pricing, checked 29 Oct 2026. Prices can change; check before you buy.
Sources for this overview
Product pages, documentation, and pricing checked 29 Oct 2026. Each source supports part of the overview; availability and prices can change.
- Overview - Featherless.ai ↗featherless.ai
- Featherless - Serverless LLM Hosting ↗featherless.ai
- Pricing | Featherless ↗featherless.ai
- About Us | Featherless ↗featherless.ai
- Featherless - Serverless LLM Hosting ↗featherless.ai
Ratings and reviews
No ratings for Featherless yet.
What’s changed
Free accountSignals
Free accountData and security
Free accountCompare with similar tools
Free accountWhere this comes from
How we research- Company website
- featherless.ai: product, pricing and policy pages
- YC directory mirror
- Batch and company name
- Social accounts
- Accounts the company links, and its posts on X
- Human review
- Checked by a person
- knowledge_base
- manual_review
Last checked 29 Oct 2026. Every field keeps its source and date; unknown means we couldn’t confirm it.