Baseten

San Francisco, CA, USA
Founded 2019

Baseten provides a platform for deploying and managing AI models in production, offering performant model runtimes, cross-cloud high availability, and seamless developer workflows.

Last Updated: March 14, 2026

Current Valuation

$5B

as of January 20, 2026 (Source)

Funding Summary

$585M

Total reported funding

Key People

Core OSS Projects

The simplest way to serve AI/ML models in production

License: MIT

Examples of models deployable with Truss

License: MIT

Taming Stable Diffusion for Lip Sync!

License: Apache-2.0

A unified library of state-of-the-art model optimization techniques such as quantization, pruning, distillation, speculative decoding, etc. It compresses deep learning models for downstream deployment frameworks like TensorRT-LLM or TensorRT to optimize inference speed on NVIDIA GPUs.

Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serving systems.

License: MIT

Ready-to-use ML training recipes to help you build and deploy models on Baseten.

License: MIT

Gorilla: Training and Evaluating LLMs for Function Calls (Tool Calls)

License: Apache-2.0

Renderer for the harmony response format to be used with gpt-oss

License: Apache-2.0

Business Information

Industries

Software

Technologies

Model Deployment
AI
Inference
LLM Workflows

Sectors

Enterprise

Licenses

MITApache-2.0

Cossmology Badge

Showcase your company's presence on Cossmology by embedding a custom badge on your website or GitHub repository.

COSS Weekly Newsletter

Stay up to date with the latest news, funding rounds, and announcements from the COSS universe.

Check out COSS Weekly on the web

All information submitted through this form is handled in accordance with the Privacy Policy of Chinstrap Community.