LLM Gateway vs vLLM Semantic Router
LLM Gateway
llmgateway.iovLLM Semantic Router
vllm-sr.aiSide by side
| Figure | LLM Gateway | vLLM Semantic Router |
|---|---|---|
| Price from | Free | — |
| Free plan | Yes | — |
| Free trial | Yes | — |
| Open source | Yes | — |
| Web | Yes | — |
| macOS | — | Yes |
| Linux | Yes | Yes |
| API | Yes | Yes |
| Self-hosted | Yes | Yes |
| Plans published | 2 | 0 |
| Spec score · LLM gateways | 9.1 (#3) | 7.3 (#26) |
| Spec score · LLM Gateway Software | 8.7 (#6) | 7.2 (#31) |
| Data retention | Pricing lists metadata retention as free and full payload retention at $0.01 per 1 million tokens; the Free plan includes activity logs and export. | The security guide says replay, response cache, memory, response history, service logs, and provider logs can retain request-derived data, and recommends setting retention and deletion policies for enabled stores. |
| Product | LLM Gateway provides one OpenAI-compatible API to route requests across 250+ models from 40+ providers. | vLLM Semantic Router describes itself as an open, programmable decision layer for models and compute. |
| Routing | 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. | It selects a model backend per request using signals that can include context, intent, safety, preferences, and system state. |
| Support | The Free plan lists Discord Community support, while Enterprise includes 24/7 priority support through a dedicated Slack or Discord channel. | The site links to GitHub Discussions as a community resource. |
Plans
In their own words
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.
vLLM Semantic Router
vLLM Semantic Router has no write-up on Specifiction yet; its figures are above.