Reduce your AI costs
What is Manifest?
Manifest is a smart model router for agents and AI applications that redirects each query to the right model, saving up to 70% in AI costs.
- Routing based on complexity, specificity and custom HTTP headers
- Mix your providers: API keys, Subscriptions, Local models, Custom providers
- Track every single dollar, setup notifications and limits
- Fallback on different models when queries fails
Quick start
Cloud version
Go to app.manifest.build and follow the guide.
Self-hosted
Manifest ships as a Docker image. One command:
bash <(curl -sSL https://raw.githubusercontent.com/mnfst/manifest/main/docker/install.sh)Open http://localhost:2099 and sign up — the first account you create becomes the admin. Full self-hosting guide: docker/DOCKER_README.md.
The legacy
manifestnpm package is deprecated and no longer published.
Providers
Manifest connects to 300+ models across 18 providers plus any custom provider (OpenAI/Anthropic compatible). Bring your own API key, reuse a paid subscription you already have, or run models locally — all routed through
the same /auto endpoint.
| Provider | API key | Subscription | Featured models |
|---|---|---|---|
| OpenAI | ChatGPT Plus / Pro / Team | gpt-5, gpt-5-mini, o4, o4-mini | |
| Anthropic | Claude Max / Pro | claude-opus-4-7, claude-sonnet-4-6, claude-haiku-4-5 | |
| — | gemini-2.5-pro, gemini-2.5-flash, gemini-2.0-flash | ||
| xAI | — | grok-4, grok-3, grok-code-fast | |
| DeepSeek | — | deepseek-v3.2, deepseek-r1 | |
| Mistral | — | mistral-large, codestral, magistral | |
| Qwen (Alibaba Cloud) | — | qwen3-max, qwen3-coder, qwq-32b | |
| Moonshot (Kimi) | Kimi Coding Plan | kimi-k2, kimi-for-coding, moonshot-v1-128k | |
| MiniMax | MiniMax Coding Plan | minimax-m2, abab7-chat-preview | |
| Xiaomi MiMo | MiMo Token Plan | mimo-v2.5-pro, mimo-v2.5, mimo-v2-flash | |
| Z.ai (Zhipu) | GLM Coding Plan | glm-4.6, glm-4.5-air | |
| BytePlus | — | ModelArk Coding Plan | ark-code-latest, bytedance-seed-code, deepseek-v4-flash |
| OpenCode | — | Go subscription | Routes via OpenCode Go catalog |
| Ollama | Local | Ollama Cloud | Any GGUF model, port 11434 |
| LM Studio | Local | — | Any GGUF model, port 1234 |
| llama.cpp | Local | — | Any GGUF model, port 8080 |
| OpenRouter | — | Routes to 300+ models across labs | |
| GitHub Copilot | — | Copilot subscription | OAuth, no API key needed |
| Custom (OpenAI/Anthropic-compatible) | — | Any /v1/chat/completions or /v1/messages endpoint |