LiteLLM vs LLM Gateway
LiteLLM
litellm.aiLLM Gateway
llmgateway.ioSide by side
| Figure | LiteLLM | LLM Gateway |
|---|---|---|
| Price from | Free | Free |
| Free plan | Yes | Yes |
| Free trial | Yes | Yes |
| Open source | — | Yes |
| Web | Yes | Yes |
| Linux | — | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 2 | 2 |
| Spec score · LLM Gateway Software | 7.8 (#15) | 8.7 (#6) |
| Spec score · LLM gateways | 7.8 (#19) | 9.1 (#3) |
| 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. |
Plans
In their own words
LiteLLM
LiteLLM is an open-source AI gateway and LLM proxy for platform teams. It provides one OpenAI-compatible API to 140+ providers and 1,800+ models, with load balancing, lowest-cost routing and automatic selection of cheaper models for simple prompts. Teams can track usage and spend across keys, users, teams, organizations, tools, agents and MCP, then apply hard budgets and rate limits. Response and semantic caching can use Redis, S3 or GCS. LiteLLM can be self-hosted, including in air-gapped environments, and offers deployment through an official Helm chart or Terraform module. The maker says self-hosting has no telemetry and keeps data within the user's infrastructure. Listed security features include hardened non-root images, vulnerability scanning, SSO/JWT/RBAC controls and secrets-manager integrations. The free Open Source plan is self-hosted and includes 100+ providers, virtual keys, budgets, rate limits, fallbacks, logging and Prometheus metrics. A 30-day Enterprise trial key is available without a credit card.
LLM Gateway
LLM Gateway provides one OpenAI-compatible API for routing requests among more than 250 models from over 40 providers. If a provider errors, times out, or rate-limits a request, it can retry up to twice with another provider for the same model. Its dashboard tracks request, token, spend, latency, error, and cache metrics, with model and provider breakdowns. Teams can use their own provider API keys without a platform fee and pay providers directly. The open-source core is licensed under AGPLv3 and can be self-hosted for free; enterprise features require a license. The Free plan is free, billed free forever, and has a 5% fee on credit usage. It includes 200+ models across 40+ providers, activity logs and export, and 20 requests per minute on free models; paid models are not rate limited. Enterprise pricing is custom and not listed. It includes custom routing, unlimited data retention, a 99.9% uptime SLA, and 24/7 priority support. Published integration guides cover tools including Claude Code, Cursor, Codex CLI, Cline, n8n, and VS Code.