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
{
"include": ["litellm", "litellm_cli"],
"ignore": [],
"exclude": ["**/node_modules", "**/__pycache__", "tests/e2e/claude_code", "tests/e2e_harness/claude_code", "tests/e2e/ui", "litellm/types/utils.py", "litellm/proxy/_types.py"],
"executionEnvironments": [
{
"root": "tests/e2e_harness",
"extraPaths": ["tests/e2e", "tests/e2e/batches", "tests/e2e/guardrails", "tests/e2e/perf", "tests/e2e/logging"]
}
],
"pythonVersion": "3.12",
"typeCheckingMode": "strict",
"enableTypeIgnoreComments": false,
"reportMissingImports": false,
"reportPrivateImportUsage": false,
"reportExplicitAny": "error",
"reportAny": "error"
}