@jetinfer

Built to maximize tokens per dollar on open-weight models

jetinfer.com/
Joined August 2026
  • Tweets5
  • Following0
  • Followers5
1Media
JetInfer retweeted
Richard Nemeth@hsdxproOct 15
Excited to see @jetinfer joining @Architect_Fi's inference provider network! We're focused on delivering fast, cost-efficient inference for open-weight models, and it's great to collaborate with teams pushing this ecosystem forward. Thanks to Brett and the Architect team for having us on board! 馃殌
Brett Harrison
@BrettHarrisonOct 14
The Liquid Inference router network is growing quickly. We now have 28 verified companies serving >1000 models, offering capacity dynamically and updating quotes in real-time. Average time for providers to onboard and integrate models is 3 hours, full verification within a day.
8
12
917
Cheaper than the cheapest on OpenRouter: Qwen3.8-27B at $0.27 in / $2.12 out per M, $0.027 cached, 15% cheaper. Self-serve now: Google sign-in, prepaid credit, API key in a minute. OpenAI + Anthropic compatible. EU, zero retention. jetinfer.com
121
JetInfer is live at api.jetinfer.com. Open-weight models at the lowest price we can run them for, starting with Qwen3.8-27B. Single-tenant GPUs, EU, OpenAI-compatible.
2
53
The plan isn't one model. It's being the cheapest reliable source for the small open-weight models people already run every day. Qwen3.8-27B first, more to follow.
4
Qwen3.8-27B at $0.34 in / $2.55 out per million, $0.034 cached. That's under Chutes, the cheapest provider on OpenRouter for it today. Endpoint's live at api.jetinfer.com, applying to list now.
47
Load more