Show HN: Qwen3.8-27B API, 140 tok/s on one GPU

Tiyuvta AI launched a hosted API for the Qwen3.8-27B model, priced at $0.38 per million input tokens, $0.20 per million cached tokens, and $2.60 per million output tokens, with a throughput of 140 tokens per second on a single GPU. New accounts receive $10.00 in free credit, with 93 of 100 places still available.

account Sign in or create an account. One step. The same screen creates the account, so there is nothing to confirm afterwards and no waiting list. free credit $10.00 of credit is added to your account on sign-up. 93 of 100 places left. - Base URL https://api.tiyuvta.ai/v1 - Models qwen/qwen3.8-27b · Step-3.7-Flash in bring-up- Price - $0.38 input · $0.20 cached · $2.60 output per million tokens - Billing - Prepaid credit. At zero balance the API returns 402 . or By continuing you accept the terms /legal/terms and the privacy terms /legal/privacy .