Photo credit: Featherless.ai

Faster Inference, Flat Prices

• Featherless.ai secured $5M Seed funding from investors including 500 Global, Airbus Ventures, and Kickstart Ventures to expand their serverless AI inference platform.
• The startup offers instant access to over 4,000 open-source AI models like DeepSeek and LLama — with new models onboarded every week — all on a flat capacity pricing model that ensures no unexpected charges or rate limits.
• Featherless.ai’s architecture facilitates seamless support for over 100 languages without any performance degradation, removing a significant barrier to global AI deployment.
• “Featherless.ai is changing the game by providing an affordable and scalable solution for using open source AI models in production,” shared Eugene Cheah, Co-founder & CEO. “I don’t want a future where AI is controlled by the few. I want to empower individuals globally.”
• Furthermore, its proprietary hot-swapping technology allows AI models to be switched in under 5 seconds, a stark contrast to the typical 30 minutes required on a standard GPU. This breakthrough optimises GPU utilisation and drastically reduces operational costs.
• With the new funding, Featherless.ai intends to advance R&D into next-generation AI architectures to lower inference costs, potentially enabling AI deployment on lower-cost hardware.
• “The biggest hurdle to scaling AI is compute cost. Featherless.ai tackles this head-on by providing the trifecta of efficient, effective and affordable AI deployment to businesses globally,” shared Vishal Harnal, Managing Partner at 500 Global.
• Read the full story on e27.