Understand this story
The English summary is being updated. See the reporting timeline below.
Latest development · Report
Hugging Face Integrates OpenRouter to Route Language Model RequestsDevelopments
1 confirmed developments
- Source:The Decoder
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 18
The Decoder
Hugging Face Integrates OpenRouter to Route Language Model Requests
Hugging Face's Inference Providers service now routes language model requests through OpenRouter, selecting providers by default based on price, speed, and reliability and automatically switching upon failure, with no changes required to existing code. Developers can adjust the strategy using the “:fastest” or “:cheapest” suffix, but bring-your-own API keys for language model providers will no longer be supported; image and video providers are unaffected. OpenRouter says the new routing reduces capacity errors by 46 percent, improves time to first token by 16.9 percent, and increases throughput by 16.3 percent.
AI Trends