Envoy AI Gateway vs ZenMux
Envoy AI Gateway
aigateway.envoyproxy.ioZenMux
zenmux.aiSide by side
| Figure | Envoy AI Gateway | ZenMux |
|---|---|---|
| Price from | Free | $20/mo |
| Free plan | Yes | Yes |
| Free trial | — | — |
| Open source | — | — |
| Web | — | Yes |
| macOS | Yes | — |
| Linux | Yes | — |
| API | Yes | Yes |
| Self-hosted | Yes | — |
| Plans published | 1 | 4 |
| Spec score · LLM Gateway Software | 8.4 (#8) | 7.5 (#27) |
| Spec score · LLM gateways | 8.4 (#10) | 7.8 (#23) |
| Observability | The CLI supports OpenTelemetry tracing and can record request and response details; the documentation describes configuration to hide input and output content. | The platform provides API request logs and analytics for costs, usage, and performance. |
| Support | The project directs users to its community Discord and GitHub issues for help. | ZenMux lists technical support by email and says it typically responds within 24 hours. |
Plans
In their own words
Envoy AI Gateway
Envoy AI Gateway, now named Agent Router, is an open-source control plane for managing AI and agent traffic through Envoy. It provides an OpenAI-compatible API for hosted and self-hosted models and MCP servers, with integrations for providers including OpenAI, Azure OpenAI, Google Gemini, AWS Bedrock, Mistral, and Anthropic. Traffic controls include model virtualization, provider failover, token quotas, and usage-based rate limiting. Its MCP gateway supports server multiplexing, tool routing, OAuth authentication, and observability; InferencePool support adds routing and load balancing for inference endpoints. Credentials can be managed centrally, and supported short-lived credential flows include AWS Bedrock, Azure OpenAI, and GCP Vertex AI. The project describes metrics collection and monitoring for AI workloads. The free open-source project is listed at free. Its CLI supports local use on Linux and macOS; production Kubernetes deployment uses Envoy Gateway and requires compatible dependencies. The project uses the Apache 2.0 license and points users to Discord and GitHub issues for help.