UnoRouter offers one OpenAI-compatible endpoint across major AI model providers

Nov 21, 2026
The open source LLM gateway routes requests across OpenAI, Anthropic, Google and others with automatic failover, behind one API key.

UnoRouter, an open source LLM gateway for engineering teams, now offers a single OpenAI-compatible endpoint for models from OpenAI, Anthropic, Google, Meta, DeepSeek, Qwen and Mistral, the company said in a press release. Teams use one API key and one base URL, and the gateway routes requests across healthy providers and fails over automatically when one degrades.

Because the API follows the OpenAI format, the company says existing code, coding agents such as Claude Code and Cline, and chat clients can connect by changing the base URL. The gateway is public on GitHub, and the hosted chat keeps conversations in the browser rather than on a server. Pricing starts with a free tier that includes free models, then moves to pay-as-you-go billing without a subscription, according to the company. The release names no customers or usage figures.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like AI Programming Weekly or Daily AI Brief.

Also, consider following us on social media:

Free newsletter

AI Programming Weekly

Weekly news about AI tools for software engineers, AI enabled IDE's and much more.

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more
Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.