LiteLLM

Ativo

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

Condicional

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.

Com IA

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

É adequada para ti?

Bom para

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

Não recomendado para

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

A nossa experiência

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

Preços

Código aberto

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

Ver preços completos

Receitas de fluxo de trabalho

Stand up a hardened proxy

Run the LiteLLM gateway without inheriting the defaults Wiz flagged

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

Histórico de veredictos

30/09/2026

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.

Fontes

Registo de verificação

Conteúdo· Atualizado29/10/2026
Agente automatizado
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.
Perfil· Atualizado15/10/2026
Agente automatizado
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.
Estado· Sem alterações1/10/2026
Agente automatizado
Perfil· Atualizado30/09/2026
Agente automatizado
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.

Como avaliamos

Quer isto a funcionar na sua empresa?

Testámos esta ferramenta e construímos com ferramentas assim todos os dias. Diga-nos o fluxo de trabalho e nós instalamos, integramos e entregamos a funcionar.

Diga-nos o que precisa Veja o que construímos

A conversa funciona com Gnosari, uma das ferramentas deste diretório. Uma conversa real, não um guião de vendas.