AI Gateway

Use any of the supported models with a universal API (REST and SDKs)

Save costs and decrease latencies by using a cache

Fallback between providers and models for resilience

Route to different targets based on custom conditional checks

Use vision, audio, image generation, and more models

Setup automatic retry strategies

Load balance between various API Keys to counter rate-limits

Canary test new models in production

Manage AI provider keys and auth in a secure vault

Easily handle unresponsive LLM requests

Set usage limits based on costs incurred or tokens used

Set hourly, daily, or per minute rate limits on requests or tokens sent