Manifest
8.7#1 in llm gatewaysFrom $19 a monthFree planWebAPILinuxSelf-hosted
Visit| Fact | Manifest | ZenMux |
|---|---|---|
| Integrations | Manifest connects API keys, paid subscriptions, local models, and custom endpoints; named local integrations include Ollama, llama.cpp, and LM Studio. | The subscription guide lists integrations for Claude Code, CodeX, Cline, VS Code Copilot, OpenCode, Cherry Studio, Obsidian, Dify, and Open WebUI. |
| Model routing | Sending model auto applies routing rules, fallback behavior and per-harness spending limits. | Its intelligent routing analyzes requests and task characteristics to select a model based on suitability and cost. |
| Observability | Usage views show spending, selected models, token consumption and failed requests for each harness. | The platform provides API request logs and analytics for costs, usage, and performance. |
Manifest suits AI builders, teams, startups, and platforms or providers that need to route model requests and track inference use. Self-hosting may suit users who want an offline gateway without an account.
ZenMux suits developers who want one interface for multiple AI model providers and routing options. Free access fits web experimentation, while paid plans add API use and higher Flow allowances.