Topics and information types
人工智能 开发工具 API 开发者 发布
Architect launches Liquid Inference with per-request auctions for LLM inferenceMachine translation
Automatically verified and published · Generated and evidence-checked automatically; not reviewed by a human.
Architect Financial Technologies has launched Liquid Inference, which auctions each LLM request among providers and selects the lowest offer that meets the buyer’s rules. Developers can connect by changing the API base URL. Buyers can set per-job cost caps, response-speed requirements and data-retention rules. Platform fees, the provider list and latency data are not yet public.
This source permits summary display only.
Read at the original source