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]
Python ai-gatewayanthropicazure-openaibedrockgatewaylangchainlitellmllmllm-gatewayllmopsmcp-gatewayopenaiopenai-proxyrustrust-aivertex-ai
#[derive(Debug, thiserror::Error)]
pub enum Error {
#[error("key expiration must be in the future")]
InvalidExpiration,
#[error("key already exists")]
AlreadyExists,
#[error("key storage unavailable")]
Storage(#[source] Box<dyn std::error::Error + Send + Sync>),
#[error("key generation unavailable")]
Entropy(#[source] rand::Error),
}