Requesty
LLM gateway and router with one OpenAI-compatible API across 400+ models
Requesty is an LLM gateway that routes requests to 400+ models across 30+ providers through a single OpenAI-compatible endpoint. It handles intelligent routing (by cost, latency, or availability), automatic failover, and prompt caching to cut token spend.
It adds per-user and per-team cost tracking, spend limits, and observability dashboards for cost, latency, error rates, and cache hits. Enterprise plans include SSO, RBAC, audit logs, guardrails, and PII detection. SOC 2, GDPR, and HIPAA compliant, with EU data residency available via a separate EU endpoint.
The free tier covers free models and 200 requests/day; paid usage is a 5% markup on base model costs with bring-your-own-keys.
Pricing: Usage-based
Requesty Alternatives
Explore 79 products in the Inference APIs category. View all Requesty alternatives.
IONOS AI Model Hub
OpenAI-compatible API for open-weight LLMs and image models, hosted in IONOS EU data centers
Opper
EU-hosted AI gateway serving 300+ models through one OpenAI-compatible API
CheapestInference
Flat-rate unlimited inference on open-weight models, sold in daily 8-hour windows
Lyceum
EU-hosted inference cloud for open-source models, OpenAI-compatible
vLLM
High-throughput LLM inference engine with PagedAttention for efficient GPU memory usage
Work on Requesty? Feature it at the top of Inference APIs.
Is your product missing?