Sign in
LiteLLM logo

LiteLLM

Active

Open-source AI gateway and Python SDK that puts 100+ LLM providers behind one OpenAI-format API

Visit websiteCompare
Conditional

LiteLLM is a strong free default for putting many model providers behind one OpenAI-format API on your own infrastructure, with virtual keys, budgets, load balancing and guardrails in the open-source plan. Conditional on security discipline: a PyPI supply-chain compromise, an MCP authentication bypass exploited in the wild, and on September 30, 2026 a critical advisory (CVSS 9.9) that lets an internal user forge proxy admin credentials. Right for platform teams that pin versions, patch within days and harden deployments.

AI-Powered

A self-hosted proxy forwards OpenAI-format requests to 100+ LLM providers and wraps those calls in keys, budgets, routing and logging.

Is it right for you?

Good for

  • Calling many model providers through one interface: LiteLLM's docs describe a single OpenAI-format API across 100+ LLMs, including OpenAI, Anthropic, Vertex AI and Bedrock
  • Platform teams controlling spend and access, with virtual keys, budgets, teams and RPM/TPM limits included in the free open-source plan
  • Keeping model traffic inside your own infrastructure, with self-hosted deployment via Docker, Helm charts or Terraform, including air-gapped
  • Resilient routing, with built-in retry and fallback logic in the SDK Router and load balancing across providers and regions
  • Trying enterprise features before buying: a 30-day self-hosted Enterprise trial key is emailed with no sales call and no credit card

Not good for

  • Deployments left on defaults: Wiz says the master key is still set by default to sk-1234 on Docker compose and pip installs, and nearly 1 in 10 of 3,074 publicly exposed deployments it scanned in February 2026 accepted a default master key or required no authentication
  • Unpinned pip installs: compromised PyPI releases 1.82.7 and 1.82.8 were live on March 24, 2026, and LiteLLM told affected users to rotate all secrets
  • Auto-pulling the newest release: v1.107.0 was malware on October 21, 2026, live on PyPI for about two hours and on the latest and main-latest Docker tags until 14:20 UTC; pin a reviewed version, delay upgrades and rotate every secret if you pulled it
  • Internet-facing proxies nobody keeps patched: per Wiz, CVE-2026-59822, an MCP authentication bypass fixed in v1.84.0, has been exploited in the wild and added to CISA's Known Exploited Vulnerabilities catalog, and CVE-2026-59821, a post-auth RCE through custom code guardrails, was fixed in v1.82.0
  • Proxies with untrusted internal users on unpatched builds: GHSA-7hp6-4w63-5g45 (CVSS 9.9, published September 30, 2026) lets an authenticated internal user forge a proxy admin token and reach the MCP stdio endpoint; upgrade to 1.100.4, 1.101.3, 1.102.2, 1.103.1 or 1.104.0rc2
  • Enterprise-licensed proxies on builds older than 1.103.10, 1.104.8, 1.105.6 or 1.106.5: GHSA-w4c7-34wj-hqm8 (CVSS 10.0, published October 27, 2026) lets unauthenticated requests read local files and leak the master key
  • Buyers who need published enterprise pricing, since LiteLLM Enterprise is priced through sales

Our experience

We haven't tested LiteLLM ourselves. This profile is based on public documentation, user reviews, and community feedback.

Pricing

Open Source
Open Source$0
  • 140+ LLM provider integrations
  • Virtual keys, budgets and teams
  • Load balancing and RPM/TPM limits
  • LLM guardrails
EnterpriseCustom
  • SSO and SCIM
  • Audit logs on every request
  • 24/7 support with response-time SLAs
  • 30-day self-hosted trial, no credit card
View full pricing

Workflow recipes

Stand up a hardened proxy

Run the LiteLLM gateway without inheriting the defaults Wiz flagged

  1. Install the proxy with uv tool install 'litellm[proxy]'
  2. Replace the example sk-1234 master key with a strong, unique key
  3. Start it against a model with litellm --model gpt-4o
  4. Review configured guardrails for unexpected entries and restart the process to clear memory
  5. Audit pass-through endpoints, restrict container network egress and apply least-privilege IAM roles to the service

Verdict history

Sep 30, 2026
conditional -> conditional (summary updated for the Sep 30 critical advisory): LiteLLM published GitHub advisory GHSA-7hp6-4w63-5g45 (CVSS 9.9) on 2026-09-30, adding to the standing security condition; rating holds.

Sources

Verification log

  • Content· Updated

    Automated agent

    New since last check: Oct 21 2026 compromise of release v1.107.0 (PyPI ~2h, Docker tags until 14:20 UTC, malware, rotate secrets, pin 1.106.2), Oct 23 attack-chain write-up, Oct 27 private registry announcement, and critical GHSA-w4c7-34wj-hqm8 (CVSS 10.0, Enterprise unauthenticated file read). CVE-2026-30623 and CVE-2026-42208 re-confirmed against the official posts (Apr 21 and Apr 29, fixes v1.83.7-stable and v1.83.10-stable). Description, strengths, experience_summary and sources refreshed.

  • Profile· Updated

    Automated agent

    Stored profile covered GHSA-7hp6-4w63-5g45 but not GHSA-g5ff-637f-6q2m (High, CVSS 8.1, no CVE, published Oct 1 2026, internal_user_viewer arbitrary file read via vertex_ai_credentials alias, fixed in 1.95.0, no workaround). Description and sources refreshed, FYI draft filed, rating holds.

  • Status· No changes

    Automated agent

  • Profile· Updated

    Automated agent

    New critical advisory published 2026-09-30 (CVSS 9.9, no CVE): salt-key reuse lets an internal user forge proxy admin. Also added vendor-sourced CVE-2026-30623 (Apr 21) and CVE-2026-42208 (Apr 29). Description, strengths, sources and summary updated; rating stays conditional; news draft created.

How we evaluate

Want this running in your business?

We tested this tool and we build with tools like it every day. Tell us the workflow and we will set it up, integrate it and hand it over working.

Tell us what you need (opens in new tab)See what we build

The conversation runs on Gnosari, one of the tools in this directory. A real conversation, not a sales script.