Recursal AI

About Recursal AI

Recursal.ai develops a post-transformer architecture that enables instant, serverless inference of Hugging Face models, achieving 100x cost efficiency for over 100 languages. Their platform allows users to effortlessly fine-tune and deploy the RWKV foundation model, making advanced AI accessible to a global audience.

<problem> Deploying and scaling large language models (LLMs) for inference can be computationally expensive, requiring significant infrastructure investment and specialized expertise. Existing solutions often lack cost-efficiency and accessibility, particularly for users working with a wide range of open-source models. </problem> <solution> Recursal.ai offers Featherless, a serverless inference platform that enables instant deployment and scaling of Hugging Face models. The platform leverages a post-transformer architecture to achieve significant cost reductions, providing up to 100x cheaper inference for over 100 languages. Users can access a vast library of open-weight models and deploy them at scale for fine-tuning, testing, and production without the burden of server management or operational overhead. </solution> <features> - Serverless architecture for instant and scalable LLM inference - Support for a wide range of open-source models on Hugging Face, including Llama 2 and 3, Mistral, Qwen, and DeepSeek - Compatibility with OpenAI SDK, LangChain, and LiteLLM - Flat pricing with unlimited tokens and predictable billing - No logging of prompts or completions for private, secure, and anonymous usage - API access for fine-tuning, testing, and production - Support for models up to 72B parameters </features> <target_audience> The primary target audience includes AI teams, developers, and researchers who need cost-effective and scalable inference solutions for open-source LLMs. </target_audience> <revenue_model> Featherless offers tiered subscription plans: Feather Basic at $10/month, Feather Premium at $25/month, and Feather Scale at $75/month, with custom enterprise plans available. </revenue_model>

What does Recursal AI do?

Recursal.ai develops a post-transformer architecture that enables instant, serverless inference of Hugging Face models, achieving 100x cost efficiency for over 100 languages. Their platform allows users to effortlessly fine-tune and deploy the RWKV foundation model, making advanced AI accessible to a global audience.

Where is Recursal AI located?

Recursal AI is based in San Francisco, United States.

When was Recursal AI founded?

Recursal AI was founded in 2023.

Who founded Recursal AI?

Recursal AI was founded by Honey Mittal and Eugene Cheah.

  • Honey Mittal - Co-Founder/CEO/CPO
  • Eugene Cheah - CEO
Location
San Francisco, United States
Founded
2023
Employees
11 employees
Looking for specific startups?
Try our free semantic startup search

Recursal AI

Score: 63/100
AI-Generated Company Overview (experimental) – could contain errors

Executive Summary

Recursal.ai develops a post-transformer architecture that enables instant, serverless inference of Hugging Face models, achieving 100x cost efficiency for over 100 languages. Their platform allows users to effortlessly fine-tune and deploy the RWKV foundation model, making advanced AI accessible to a global audience.

recursal.ai200+
Founded 2023 – San Francisco, United States

Funding

No funding information available. Click "Fetch funding" to run a targeted funding scan.

Team (10+)

Honey Mittal

Co-Founder/CEO/CPO

Eugene Cheah

CEO

Company Description

Problem

Deploying and scaling large language models (LLMs) for inference can be computationally expensive, requiring significant infrastructure investment and specialized expertise. Existing solutions often lack cost-efficiency and accessibility, particularly for users working with a wide range of open-source models.

Solution

Recursal.ai offers Featherless, a serverless inference platform that enables instant deployment and scaling of Hugging Face models. The platform leverages a post-transformer architecture to achieve significant cost reductions, providing up to 100x cheaper inference for over 100 languages. Users can access a vast library of open-weight models and deploy them at scale for fine-tuning, testing, and production without the burden of server management or operational overhead.

Features

Serverless architecture for instant and scalable LLM inference

Support for a wide range of open-source models on Hugging Face, including Llama 2 and 3, Mistral, Qwen, and DeepSeek

Compatibility with OpenAI SDK, LangChain, and LiteLLM

Flat pricing with unlimited tokens and predictable billing

No logging of prompts or completions for private, secure, and anonymous usage

API access for fine-tuning, testing, and production

Support for models up to 72B parameters

Target Audience

The primary target audience includes AI teams, developers, and researchers who need cost-effective and scalable inference solutions for open-source LLMs.

Revenue Model

Featherless offers tiered subscription plans: Feather Basic at $10/month, Feather Premium at $25/month, and Feather Scale at $75/month, with custom enterprise plans available.