Envoy AI Gateway

Mac · Linux · Self-hosted · API

Freedom report

One barScore 5.1

Free tierA free tier is on its own pricing page
Open codeNo open-source code on record
Runs widely2 of 6 device platforms
DocumentedThinly documented

Envoy AI Gateway is ranked #31 of 33 in LLM gateway software on Freedom251. It runs on API, Linux, macOS, Self-hosted. There is a free plan.

Envoy AI Gateway plans and pricing

All plans

Open-source project Free Self-managed; local CLI supports Linux and macOS · Kubernetes deployments require compatible dependencies theagentrouter.ai · 9 Oct 2026

Compared on LLM gateway software

Free plan: Yes
Fallback routing: Yes
Usage analytics: Yes
Self-hosted deployment: Yes
Budget controls: Yes

Best Envoy AI Gateway alternatives

See all 20

Two bars Bifrost Free tier No. 1Free6.6 Two bars Routerly Free tier No. 2Free6.6 Two bars YoloRouter Free tier No. 3Free6.6 One bar Kong Gateway Free tier No. 4Free6.5 One bar SGLang Free tier No. 5Free6.5 One bar TensorZero Free tier No. 6Free6.5

The record

Purpose: Envoy AI Gateway, now named Agent Router, is an open-source control plane for managing AI and agent traffic using Envoy.
Unified API: It provides an OpenAI-compatible API for accessing hosted and self-hosted models and MCP servers.
Provider integrations: The project lists integrations including OpenAI, Azure OpenAI, Google Gemini, Vertex AI, AWS Bedrock, Mistral, Cohere, Groq, Together AI, DeepInfra, DeepSeek, Hunyuan, SambaNova, Grok, and Anthropic.
Traffic controls: Capabilities include model virtualization, provider failover, token quotas, and usage-based rate limiting.
MCP gateway: Its MCP gateway supports server multiplexing, tool routing, OAuth authentication, and observability.
Inference routing: InferencePool support provides intelligent routing and load balancing for inference endpoints.
Security: The project describes upstream authentication for securing connections to AI services and says provider credentials can be kept out of application workloads.
Observability: The project describes metrics collection and monitoring for AI workloads.
Deployment: The CLI can run locally on Linux and macOS, and production deployment uses Kubernetes with Envoy Gateway.
Intended users: The documentation identifies teams sharing models or tools, seeking centralized credentials, quotas, usage attribution, or failover as likely users.
License: The project uses the Apache 2.0 license.
Support: The project directs users to its community Discord and GitHub issues for help.
Renamed project: Envoy AI Gateway is now Agent Router, an Agentic AI Foundation project; the site says the code, maintainers, and APIs remain the same.
Credential security: Upstream credentials can be centrally managed; supported providers include short-lived credential flows for AWS Bedrock, Azure OpenAI, and GCP Vertex AI.
Price from: Free

Where it ranks on Freedom251

Best LLM Gateway Software in 2026#31 of 33

Is Envoy AI Gateway yours?

Claim it for free: prove the domain, then correct facts, plans and screenshots. An editor reviews every change.

Claim it free Promote Envoy AI Gateway

Sources

github.com/theagentrouter/agent-router· checked 9 Oct 2026
theagentrouter.ai/docs/capabilities/· checked 9 Oct 2026
theagentrouter.ai/docs/· checked 9 Oct 2026
theagentrouter.ai/docs/getting-started/· checked 9 Oct 2026
theagentrouter.ai/blog/envoy-ai-gateway-is-now-agent-rout· checked 9 Oct 2026
theagentrouter.ai· checked 9 Oct 2026
theagentrouter.ai/docs/capabilities/security/upstream-aut· checked 9 Oct 2026
theagentrouter.ai/docs/cli/aigwrun/· checked 9 Oct 2026
theagentrouter.ai/docs/compatibility/· checked 9 Oct 2026
aigateway.envoyproxy.io· checked 28 Sept 2026