
LiteLLM
6.8#18 in llm gatewaysFree planFree planWebAPISelf-hosted
Visit
| Fact | LiteLLM | LLM Gateway |
|---|---|---|
| Caching | Response and semantic caching can use Redis, S3, or GCS. | Projects can enable response caching to reduce repeated-request latency and token expense. |
| Integrations | The integrations documentation lists observability tools including Langfuse, Datadog, Grafana Cloud, OpenTelemetry, LangSmith, Arize/Phoenix, and Helicone. | Published integration guides cover Claude Code, Cursor, Cline, n8n, VS Code, Codex CLI, OpenCode, Continue, Kilo Code, Kimi Code and other coding tools. |
| Product | LiteLLM is an open-source AI gateway and LLM proxy for platform teams. | LLM Gateway provides one OpenAI-compatible API to route requests across 250+ models from 40+ providers. |
| Routing | LiteLLM supports load balancing, lowest-cost routing, and automatic routing of simple prompts to cheaper models. | The gateway can retry up to twice with another provider for the same model when a provider errors, times out, or rate-limits a request. |
| Security | The product page describes signed hardened non-root images, vulnerability scanning, SSO/JWT/RBAC controls, and secrets-manager integrations. | The company states that it is SOC 2 Type II audited and GDPR-aligned, and describes TLS in transit and AES-256 encryption at rest. |
| Spend controls | It tracks usage and spend by key, user, team, organization, tool, agent, and MCP, and supports hard budgets and rate limits. | API keys and members can receive spending caps and optional alerts, while Enterprise adds team budgets. |
| Support | Enterprise includes dedicated support and onboarding, with 24/7 support and SLAs listed on the pricing page. | The Free plan lists Discord Community support, while Enterprise includes 24/7 priority support through a dedicated Slack or Discord channel. |
You want what its maker publishes above — check its page for the details.
LLM Gateway suits product and platform teams routing application requests to multiple model providers. Organizations deploying LLM infrastructure across teams may consider its enterprise identity, guardrail, and support options.