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. This documentation will help you to get started and use Manifest to use AI efficiently and reduce your inference costs.Documentation Index
Fetch the complete documentation index at: https://manifest.build/docs/llms.txt
Use this file to discover all available pages before exploring further.
Key features
Routing
Routing based on complexity, specificity and custom HTTP headers
Fallbacks
Fallback to different models on failure.
Set limits
Get email alerts or block requests when spending crosses a threshold.
All your providers
Plug in every kind of provider: API key, subscription-based, local models or
custom.