OP
OpenModel
OpenModel is a multi-model LLM gateway and operations console for unified provider access, logs, billing, and usage visibility.
View selection notes →Software directory
API Gateway Key Management
Compare tools by fit, operating cost, data boundaries, and migration risk.
AP
Apache APISIX AI Gateway
Use Apache APISIX as an open-source LLM gateway and proxy for model routing, load balancing, retries, fallback, token rate limiting, security, and observability.
View selection notes →LL
LLM Gateway
Route, manage, and analyze LLM requests across OpenAI, Anthropic, Google, and 40+ providers through one unified API.
View selection notes →GR
Gravitee AI Gateway
Gravitee is the AI Agent Management platform, securing, observing, and governing every AI agent, API, and event interaction at enterprise scale.
View selection notes →EN
Envoy AI Gateway
Envoy AI Gateway is an open source project for using Envoy Gateway to handle request traffic from application clients to GenAI services.
View selection notes →NE
NeuralTrust AI Gateway
Protect your AI systems with organization-wide policies, minimum reliance on individual developers, and full user context to prevent attacks effectively.
View selection notes →KO
LU
Lunar.dev AI Gateway
Learn how to deploy, configure, and scale Lunar.dev’s AI Gateway and MCPX (MCP Gateway) for secure, observable, and governed AI traffic.
View selection notes →NE
NeuralRouting
Route every AI request to the cheapest capable model. NeuralRouting cuts LLM costs up to 85% with intelligent routing, semantic caching, and failover. OpenAI SDK compatible.
View selection notes →PE
Pellet AI
Pellet AI routes each request to the smallest capable open-source model — same quality, 87% less cost. OpenAI-compatible API with 12 models, intelligent auto-routing, and full analytics.
View selection notes →RE
RelayGate
Open-source LLM gateway: virtual keys, CEL policy engine, multi-provider routing, cost tracking, and signed audit events.
View selection notes →NE
Nemo Router
The secure enterprise LLM gateway — one API key, every model. Nemo Router routes 78+ AI models through one endpoint, with built-in guardrails, budget enforcement, smart routing, and real-time cost tracking — included on every plan.
View selection notes →