Icon for Powerspring

Powerspring

OpenAI-compatible API for open-weight models like DeepSeek, GLM, Qwen and gpt-oss, run on EU-owned infrastructure

Powerspring serves open-weight models through one OpenAI-compatible API, processed on EU infrastructure owned by EU companies: DeepSeek V4.1 Flash, GLM 5.3 Flash, gpt-oss-120b, gpt-oss-20b, Qwen3.8-27B and two Gemma 4 models. It does not store request or response content, and requests stay in the EU on failover too. The infrastructure providers are not named publicly; the sub-processor list is available by email.

Tokens are sold at cost, gpt-oss-120b at €0.08 in and €0.40 out per 1M tokens, with a 5% service fee on each prepaid top-up from €10. Pre-booked volume costs 25% less. Run by Poolside Ventures SL in Barcelona.

Pricing: Per token usage

Pricing €10 prepaid top-up, plus a 5% service fee
HQ 🇪🇸 Spain
Screenshot of Powerspring webpage

Work on Powerspring? Feature it at the top of Inference APIs.

Is your product missing?

Add it here →