Featherless - Featherless - Serverless LLM Hosting

About Featherless

Featherless AI is a serverless AI inference platform. Our goal is to make all AI models available for serverless inference and we’ve started with large language models (e.g. Qwen, Llama, Mistral, DeepSeek, RWKV). We provide inference via API to a continually expanding library of open-weight models, including the most popular models for role-playing, creative writing, coding assistance, and more.

Featherless offers open-model access through a single API, enabling developers to run thousands of models without separate hosting. The API is OpenAI-compatible and designed for reliability and real workloads, with a focus on low latency and uptime.

Users can explore a catalog of models and test them through a web interface, with options for chat, coding agents, vision and other use cases. The platform emphasizes serverless inference and access to open models via a unified API.

Featherless provides a catalog of models, plans with varying context sizes and concurrency, and GPU-backed options for teams needing predictable latency and dedicated resources.

Key features

One API key. Instant access.
Access thousands of open-source models from a single API. Every hugging face trending model without setup or hosting.
Low latency, dependable uptime, and architecture designed for real workloads.
Flat-rate pricing designed for scale with unlimited tokens.
Chat plan is for interactive, human-driven use by the purchaser.
Built for reliability and performance

Pros and cons

Pros

Open catalogue of models available on every plan.

Single API for thousands of models.

Pricing

Business

Custom

annual

Dedicated GPUs and the team to run them
Engineering team included
SLA
Private fine-tunes
Talk to an Engineer

Reviews

Loading reviews…

Frequently asked questions

What counts as human-driven use?

Back-and-forth between you and the model is fine, whatever the frontend. What isn't covered is app or API traffic, reselling, background automation and benchmarking.

Can I just use the chat box on the model pages?

Chat boxes on model pages are for testing a model, not a full chat interface. The plan gives you an API key, which you point to SillyTavern, RisuAI, or any OpenAI-compatible frontend.

Does it renew automatically?

Yes, monthly. Cancel or pause from the billing page and no further charge is attempted.

Alternatives to Featherless

Unibase Memory

Membase provides private, encrypted memory that syncs across ChatGPT, Claude, Gemini, Grok and Kimi to save, search, and reuse AI context.

211.3M

Hugging Face

Hugging Face is a platform for the machine learning community to collaborate on models, datasets, and applications.

31.2M

Miro

Miro is an AI-powered visual collaboration platform for teams to ideate, plan, and ship products with AI-enabled canvases and templates.

27.8M

Airtable Assistant

Airtable Assistant is a powerful AI-driven tool designed to serve as a personal app builder, data analyst, and web researcher. It enables users to effortlessly extract valuable insights from extensive datasets, answering complex business questions with ease. With its ability to analyze thousands of records, Airtable Assistant helps organizations identify customer pain points and streamline decision-making processes, enhancing overall productivity and efficiency.

21.3M

Outlier AI

Outlier AI is a collaborative platform that connects subject matter experts to contribute to the development of advanced Generative AI technologies. By engaging in diverse projects, contributors can generate training data and evaluate model performance, all while working alongside a supportive team led by experienced squad leaders. This flexible opportunity allows independent contractors to choose their working hours and participate in ongoing projects, enhancing their expertise in the AI field.

20.3M

Venice AI

Venice AI provides private, uncensored AI across text, image, video, and more, with a privacy-first architecture for creators and developers.

20.3M