One API key to manage all your LLM providers. Smart routing, cost tracking, health monitoring, and team management.
Set model: auto and WebRouter picks the optimal model based on request complexity. Simple queries get fast/cheap models, complex reasoning gets powerful ones.
Automatic health checks with latency tracking. Dead providers enter cooldown; traffic shifts to healthy alternatives - no manual intervention needed.
Real-time cost accounting per model, per token, per team. Billing reports, quota management, and budget alerts built in.
Built-in desensitization engine strips PII (phone numbers, ID cards, emails) from requests before they reach upstream providers.
Invite team members, assign quotas, restrict model access. Each member gets a unique API key with scoped permissions.
direct, aggregate, litellm, custom - any OpenAI-compatible provider. One gateway, all your LLMs.
Clients lose context? Just use @recall or X-Recall-Session header. wr-proxy automatically recovers and injects conversation history from the server.
Auto-capture conversations, extract structured knowledge via LLM, and inject relevant context into every request. Enterprise-grade retrieval-augmented generation built in.
Token compression, session compression, and dynamic content reordering. Reduce upstream token consumption and improve prompt cache hit rates automatically.
