A guide for running LiteLLM, an AI gateway that gives applications one OpenAI-compatible interface for many language-model providers. It also covers its Python SDK and proxy service.

Configuring and troubleshooting the gateway, routing requests between providers, managing teams and virtual keys, setting limits, and investigating model or spending problems.

It helps teams manage model routing, access keys, budgets, rate limits, caching, safety checks, monitoring, and spending in one place.

litellm — Skill for Claude Code and Codex by magnus919/agent-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add magnus919/agent-skills --skill litellm

Clone the repo

git clone --depth 1 https://github.com/magnus919/agent-skills

Made for: Claude Code, Codex.

Its marketplace also offers this one on its own, as the plugin litellm — /plugin install litellm after adding the marketplace above.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/magnus919/agent-skills/litellm/github.svg)](https://agentmods.dev/skills/magnus919/agent-skills/litellm)

Your own site

<a href="https://agentmods.dev/skills/magnus919/agent-skills/litellm"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/litellm/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/magnus919/agent-skills/litellm"><img src="https://agentmods.dev/badge/skills/magnus919/agent-skills/litellm.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,321 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 46
Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00173	$0.04321
Opus 5.5	$0.00069	$0.01728
Sonnet 5.5	$0.00035	$0.00864
Haiku 4.5	$0.00017	$0.00432

Measured 1mo ago against content hash a6d59f2dd3b9, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

litellm scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

The scan reads SKILL.md. This mod also ships 1 executable file (tests/test_litellm_health.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

litellm/SKILL.md · 287 lines

How it starts

The opening of the file, as written. The whole thing — 287 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LiteLLM AI Gateway Operations

Use this skill to operate LiteLLM as an organization's AI gateway: run the proxy (litellm --config config.yaml), route requests to 100+ LLM providers through one OpenAI-compatible API, manage model lists, routing and reliability, virtual keys, teams, budgets and rate limits, caching, guardrails, observability, and spend — and diagnose failures with evidence. LiteLLM ships two surfaces: a Python SDK (litellm.completion(), in-process) and the proxy (a FastAPI service on port 4000 with keys, budgets, and an admin UI). This is a tool skill for the named tool. Engine selection and serving methodology belong to ml-engineering; operating a single engine belongs to vllm or llama-cpp.

Operating contract

Record the deployment before tuning it. Capture the pinned image or pip version, config.yaml, model list, routing, budgets, env-var references, and data stores in the proxy config record. That record is the rollback unit.
Confirm the target, scope, and rollback path before mutating. Read-only discovery (health probes, /v1/models, logs, spend queries) may proceed without confirmation. Mutations — config changes, key mint/revocation, restarts, image upgrades, DB migrations — require an explicit human directive naming the deployment.
A proxy that responds is not a proxy that serves. /health/liveliness returning 200 proves liveness only. Verify at the delivery boundary: a representative /v1/chat/completions request returns tokens and x-litellm-model-id names the deployment you expected.
Keep evidence bounded. Summarize logs and configs; never dump full logs, .env contents, master keys, or provider credentials into chat. Spend logs and debug output can contain prompt content — redact before sharing.
Pin versions. LiteLLM releases weekly and changes defaults; every claim here was checked against 1.97.0 (2026-08-22). Re-verify version-sensitive behavior against your installed release before relying on it.

Read the full file on GitHub · 287 lines

Files

What ships with it

15 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

1mo ago First seen · 287 lines · 173 tokens per session scan A a6d59f2dd3b9

Subscribe to this mod's changes

litellm is a skill published in the GitHub repository magnus919/agent-skills (154 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 4,321 once invoked, about $0.0007 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.

Backend and APIs Data and AI LLM agent-skills agentskills ai-agents automation

serving-llms-vllm

Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.

NousResearch/hermes-agent · 27 tokens

open-source

Documentation reference for writing Python code using the browser-use open-source library. Use this skill whenever the user needs help with Agent, Browser, or Tools configuration, is writing code that imports from browseruse, asks about @sandbox deployment, supported LLM models, Actor API, custom tools, lifecycle…

browser-use/browser-use · 137 tokens

data-leakage-detection

Detect sensitive information disclosure via escalating dialogue probes. Covers system prompt extraction, credential/API key leakage, PII, and internal configuration exposure.

Tencent/AI-Infra-Guard · 34 tokens

bridging-presidio-and-spacy

Combine OpenMed clinical NLP with Microsoft Presidio, spaCy, or LangChain through OpenMed's built-in interop adapter registry (openmed.interop). Covers the lazy adapter registry (availableadapters, getadapter, adapterspec), the presidio/spacy/langchain pip extras, and the verified callables — Presidio…

maziyarpanahi/openmed · 154 tokens

server-inference

Use this skill when the user wants to run or debug MLX-VLM server inference, including uv run mlxvlm.server, /v1/models, /v1/chat/completions, /v1/responses, streaming, OpenAI-compatible clients, health checks, metrics, model unload/reload, adapters, trust-remote-code, and server request/response failures.

Blaizzy/mlx-vlm · 80 tokens

llmsim

Answer every LLM call for free and deterministically with llmsim, haven's provider stand-in. Use when someone says 'haven llm', 'run without a real model', 'no API key', 'cheap playground', 'llmsim', 'haven up +llm', 'force a 429', 'mock the LLM', 'haven sim llm', 'Langy echo', or needs repeatable model output in a…

langwatch/langwatch · 98 tokens