Requesty Plans Pricing
Requesty uses a usage-based pricing model layered on top of unified LLM routing. A Free tier provides 200 requests per day on free models with no credit card required. Pay-as-you-go applies a 5% markup on the underlying base model cost (a model that costs $10 per 1M tokens upstream costs $10.50 through Requesty), with no subscription, seat fees, or minimum spend, and supports bring-your-own-keys (BYOK) across 300+ models. Enterprise adds SSO, RBAC with audit logs, guardrails, PII detection, dedicated support, and custom SLAs on negotiated pricing.
Requesty Plans Pricing is the machine-readable pricing-plan profile for Requesty on the APIs.io network, conforming to the API Commons Plans specification.
It defines 3 plans, covering free, usage, and enterprise tiers, with named plans including Free, Pay-as-you-go, Enterprise.
Tagged areas include AI, LLM, Routing, Gateway, and Observability.
Plans
Free access to routing, caching, fallbacks, and EU data residency with a daily request cap on free models. No credit card required.
- Chat Completions (free models)
- Routing
- Caching
- Fallbacks
- EU Data Residency
Usage-based access to 300+ models with a 5% markup on base model cost, BYOK support, observability, spend limits, and budget caps. No subscription, seat fees, or minimum spend.
- Chat Completions
- Embeddings
- Routing & Fallbacks
- Caching
- Observability
- Spend Limits & Budget Caps
Custom pricing with SSO, full RBAC with audit logs, guardrails, PII detection, service accounts for CI/CD, dedicated support, and custom SLAs. Contact sales@requesty.ai.
- SSO
- RBAC & Audit Logs
- Guardrails & PII Detection
- Service Accounts
- Dedicated Support & SLAs