完整作品展
技术栈
3 projects
FlexInference: 通过多个提供商路由LLM API请求，降低成本和延迟。
Aperswal · HN
Made a Free LLM Router
Format-agnostic LLM hub. Bring your own provider keys and route across Anthropic, OpenAI, ChatGPT/Codex, Kimi, Alibaba DashScope, and AWS Bedrock — with unified observability and c
@0xxmemo · X
