How much does Requesty cost?
Requesty charges a 5% markup on base model costs. No subscription, no seat fees, no minimum spend. A model that costs $10 per 1M tokens from OpenAI costs $10.50 through Requesty. Every feature is included on every plan, including routing, caching, guardrails, and EU data residency. Enterprise plans with SSO, RBAC, and custom SLAs are priced on request.
Most popular
Pay as you go
Only pay for what you use
5% markup
All 400+ models
Bring your own keys
Routing policies, caching & fallbacks
Spend limits & budget caps
MCP Gateway
EU data residency
Advanced observability
Email support
Enterprise
For teams with advanced needs
Custom
SSO — Okta, Azure AD, Google Workspace
Full RBAC + audit logs
Approved models & policies
Teams, groups & spend controls
Guardrails & PII detection
EU data residency
Service accounts for CI/CD
Dedicated support & custom SLAs
Compare plans
See exactly what's included in each tier
| Features | Pay as you go | Enterprise |
|---|---|---|
| Models & Providers | ||
| 400+ AI models | ||
| 20+ providers | ||
| Bring your own keys | ||
| Approved models whitelist | ||
| Custom model hosting | ||
| Routing & Reliability | ||
| Routing policies | ||
| Automatic fallbacks | ||
| Load balancing | ||
| Latency routing | ||
| Prompt caching | ||
| Custom routing rules | ||
| Security & Compliance | ||
| Guardrails | ||
| PII detection | ||
| EU data residency | ||
| SSO (Okta, Azure AD, Google Workspace) | ||
| Full RBAC | ||
| Audit logs | ||
| SOC 2 compliance | ||
| Teams & Access | ||
| Spend limits per key | ||
| Service accounts for CI/CD | ||
| User management | ||
| Groups & team budgets | ||
| Key management API | ||
| Analytics & Monitoring | ||
| Real-time analytics | ||
| Cost tracking | ||
| Advanced observability | ||
| Tool call analytics | ||
| Session reconstruction | ||
| Spending alerts (Slack + webhooks) | ||
| Custom dashboards | ||
| Data exports | ||
| Developer Tooling | ||
| MCP Gateway | ||
| Prompt library | ||
| Prompt optimization | ||
| Structured outputs | ||
| Reasoning / extended thinking | ||
| Support | ||
| Community support | ||
| Email support | ||
| Dedicated support | ||
| Custom SLAs | ||
Frequently asked questions
Everything you need to know about pricing
Ready to get started?
Pay as you go — only a 5% markup on model costs. No minimum commitment.