2026 最佳AI 閘道與路由工具

I

inferock-bench

AI 閘道與路由

inferock-bench is a local diagnostic proxy for tracking LLM API usage, provider-reported costs, failures, and billing-integrity signals. It helps developers inspect calls to OpenAI, Anthropic, Gemini Developer API, and pinned OpenRouter endpoints using locally stored receipts.

G

Guardrail by NeatProxy

AI 智能體基礎設施

Guardrail is a local spend firewall for AI coding agents. It records usage metadata and, on supported proxy integrations, checks budget policies before forwarding requests to providers.

C

Cohesor

AI 智能體基礎設施

Cohesor is an AI gateway and control plane for routing model requests, compressing agent context, governing spend, and brokering MCP tool calls. It is designed for teams running internal or customer-facing AI agents.

A

API in One

AI 音訊 API

API in One is a unified AI API gateway for website owners and developers who need image, video, music, speech, chat, and AI tool capabilities through one API key and shared credit balance.

4

4ALL API

AI 音訊 API

4ALL API is an API aggregation gateway for enterprises and developers that provides one access layer for text, image, video, and audio models from multiple providers. It supports OpenAI-compatible access, usage-based billing, model routing, and failover workflows.

W

Wokey AI

AI 閘道與路由

Wokey AI provides a single API key for models from providers including Anthropic, OpenAI, Moonshot AI and xAI, with compatible endpoints and locally verifiable response proofs.

D

deadeye

AI開發者工具

deadeye is a plugin for coding agents that selects a suitable model and effort level for each task, while trimming verbose command output before it enters context. It is built for Claude Code and also supports Codex CLI, Gemini CLI, Cursor, and Windsurf on an experimental basis.

H

Hugging Face Inference Providers

AI 閘道與路由

Hugging Face Inference Providers gives developers a way to compare supported models across infrastructure providers using model availability, pricing, context limits, latency, throughput, and capability indicators.

E

Edgee

AI開發者工具

Edgee is an agent gateway for coding teams that reduces token usage, routes requests across models, and provides usage visibility. Its Compression V2 works as a drop-in CLI layer for Claude Code, Codex, OpenCode, Cursor, and other supported agents.

F

fez

AI 閘道與路由

Fez is an experimental decision-model platform that turns workflow context into probabilities for model routing, tool selection, escalation, and support triage. It helps teams train and evaluate specialized models for repeated decisions in AI systems.

H

Hopscotch

AI 閘道與路由

Hopscotch is a unified API for accessing 500+ AI models from providers including Anthropic, OpenAI, and Google. It helps developers and teams switch models, configure fallbacks, and control spending through shared keys, teammate limits, and workspace limits.

A

Apache APISIX

AI 閘道與路由

Apache APISIX is an open-source API gateway and AI gateway for routing, securing, observing, and governing API, microservice, and LLM traffic. It helps teams manage dynamic gateway policies through a plugin-based architecture built on NGINX and etcd.

D

Docker MCP Enterprise Gateway

AI 智能體基礎設施

Docker MCP Enterprise Gateway governs how MCP-compatible clients access approved servers and tools. It applies identity-aware policy, supplies credentials from an approved secret store, and records tool-call decisions for enterprise teams.

T

TensorZero

AI 閘道與路由

TensorZero is an open-source LLMOps platform for building and operating production-grade LLM applications. Its stated scope combines an LLM gateway with observability, evaluation, optimization, and experimentation tools.

N

New API

AI 閘道與路由

New API is an open-source, self-hosted AI gateway for developers and teams. It provides a unified OpenAI-compatible endpoint for connecting multiple AI providers, selecting models, configuring channels, and monitoring usage on their own infrastructure.

O

Obot

AI 智能體基礎設施

Obot is an open-source enterprise AI control plane and MCP gateway for deploying, governing, and auditing AI agents, MCP servers, and Skills. It helps organizations centralize access policies, discovery, authentication, and activity records across AI tooling.