LiteLLM一个跨100+LLM（使用统一OpenAI格式）提供API、SDK和代理服务器，进行身份验证、负载均衡以及支出追踪的开源Python SDK和代理服务器。

How do I get day-0 support for new models without restarting?

Use Auto Sync New Models to pull the latest pricing and context-window data from GitHub on demand or on a schedule — no restart required. Trigger a manual sync with POST /reload/model_cost_map, or schedule periodic syncs with POST /schedule/model_cost_map_reload?hours=6.

Asked by Gabriel Duarte · Feb 1, 2026

How is pricing structured?

Pricing is based on usage. Contact us for a quote tailored to your team.

Asked by Fiorella Bianchi · Feb 1, 2026

Where can I read more about data security and compliance?

See Data Security / Legal / Compliance FAQs.

Asked by Zara Ahmed · Jan 17, 2026

How do I set up and verify an Enterprise License?

Add the license key to your environment: LITELLM_LICENSE="eyJ..." Restart LiteLLM Proxy. Open http://<your-proxy-host>:<port>/ — the Swagger page should show "Enterprise Edition" in the description. If it doesn't, confirm the key is correct, unexpired, and that the proxy was fully restarted.

Asked by George Papadakis · Dec 11, 2025

Why Enterprise?

LiteLLM OSS already covers the fundamentals — an OpenAI-compatible gateway, virtual keys, spend tracking, budgets, fallbacks, and request/response logging. Enterprise adds the controls larger organizations need to safely give hundreds of users and dozens of applications access to LLMs. OSSEnterpriseAuthAPI keysSSO + SCIM, OIDC/JWTKey ManagementVirtual keys, users, teams across LLM APIs, MCPs, and AgentsOrganizations, org/team admins, delegated admin rolesSecurity—Key rotations, read/write to secret managerGuardrailsAlways-on / request-based1Key and team scoped guardrailsLoggingRequest/response logging, Prometheus metricsPer-key / per-team routing to Langfuse, Langsmith, Arize and more. Management-op logsDeploymentSingle-region proxyMulti-region deployment under one license, admin/worker split 1 The OSS guardrail framework supports custom guardrails plus Presidio (PII masking). Several built-in callback integrations — including llmguard_moderations, llamaguard_moderations, hide_secrets, openai_moderations, google_text_moderation, lakera_prompt_injection, and aporia_prompt_injection — require a LiteLLM Enterprise license.

Asked by Ahmed Saleh · Nov 25, 2025