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(thiserror::Error, veil::Redact)]
pub enum Error {
#[error("CyberArk Conjur operation timed out")]
Timeout,
#[error("CyberArk Conjur HTTP request failed")]
Http(
#[from]
#[redact]
reqwest::Error,
),
#[error("CyberArk Conjur authentication returned HTTP {0}")]
AuthStatus(u16),
#[error("CyberArk Conjur returned HTTP {0}")]
Status(u16),
#[error(
"CyberArk credentials are missing: set CYBERARK_API_KEY or both CYBERARK_CLIENT_CERT and CYBERARK_CLIENT_KEY"
)]
MissingCredentials,
#[error("CyberArk client certificate could not be loaded")]
ClientCertificate,
#[error("CyberArk Conjur HTTP client could not be built")]
Client(#[redact] Box<litellm_http::Error>),
#[error("invalid refresh interval")]
RefreshInterval,
#[error("invalid CyberArk Conjur endpoint")]
Endpoint,
#[error("CyberArk secret manager requires an enterprise license")]
EnterpriseRequired,
#[error(transparent)]
Operation(#[from] litellm_secrets_types::Error),
}