Qwen3.8 27B

General purpose. Runs on Confidential Inference: an OpenAI-compatible endpoint inside TEEs, with an attestation on every response.

StatusInput (per 1M tokens)Input Cached (per 1M tokens)Output (per 1M tokens)
On request$0.30$0.03$1.80

Get access

Full pricing: pricing. Docs: get started.