Requesty
Managed LLM router with failover chains and spend governance.
A hosted, OpenAI-compatible router across many providers: route by cost, latency or availability, set failover chains and weighted load balancing, and use prompt caching. Teams get PII masking, approved-model lists and access policies. Usage-based, with a percentage fee on model costs.
- Vendor
- Requesty
- Category
- AI gateways
- Pricing
- Paid
- Open source
- No
- Platforms
- API
- Website
- requesty.ai
Features
- Cost/latency routing
- Failover chains
- Prompt caching
- PII masking
Best for
- High volume / low cost
- Enterprise
More ai gateways
- OpenRouter — OpenRouter. One API for hundreds of models.
- LiteLLM — BerriAI. Open-source, self-hosted gateway to 100+ LLM APIs in the OpenAI format.
- Portkey — Portkey. Production AI gateway with routing, guardrails, budgets and observability.
- Cloudflare AI Gateway — Cloudflare. Edge gateway for caching, rate-limiting and observing AI API calls.
- Vercel AI Gateway — Vercel. One endpoint for hundreds of models, with no markup on tokens.
- Azure API Management AI gateway — Microsoft. AI gateway policies built into Azure API Management.
- Kong AI Gateway — Kong. AI plugins that turn the Kong API gateway into a multi-LLM gateway.
- Apigee AI gateway — Google Cloud. AI gateway policies in Google Cloud’s Apigee API platform.