LiteLLM

• tags::
• source:: BerriAI/litellm: Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

LLM API 代理服务器，处理不同模型供应商 API 数据结构转换，进行统一

其他实现

• majiayu000/litellm-rs
  • Rust
  • 2026.1.1 未提供 http api
• maximhq/bifrost: Fastest LLM gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 µs overhead at 5k RPS.
  • Go
• tensorzero/tensorzero: TensorZero is an open-source stack for industrial-grade LLM applications. It unifies an LLM gateway, observability, optimization, evaluation, and experimentation.
  • Rust
  • 提供 LLM 一站式服务
• Laisky/one-api: OpenRouters opensource alternative. Multi-model/Multi-API-format/Multi-tenant LLM API aggregation platform.
  • Go
  • 定位 OpenRouter 开源替代