Skip to content

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthropic, OpenAI, VertexAI, vLLM, Nvidia NIM]

310 B
Raw Blame
//! The Rust driver for hosted calls: it answers host services and interceptors with Rust handlers
//! and hands stream deliveries to whichever consumer sits on top, HTTP body polling or an
//! in-process stream consumer.

mod driver;
pub mod in_process;
pub mod services;

pub use driver::{Boundary, Driver};