sference

sference is a managed inference platform for open-weight models, fine-tunes, and distilled models. They provide low-latency realtime inference on European GPUs and have a single OpenAI-compatible API. They offer serverless per-token to dedicated deployments and have full logging and audit trail.

  • Headcount
  • Financials
  • Funding
  • Mergers & Acquisitions
  • Products and services
  • Similar companies

Get it all with one API call

from tavily import TavilyClientclient = TavilyClient(api_key="tvly-YOUR_API_KEY")response = client.extract(urls=["https://tavily.com/knowledge/company/0mPXCeFUL35A"])print(response)