Pricing that pays for itself
Most teams save more than the subscription costs in the first week. Start free, upgrade when you scale.
Free
- ✓Up to 50k requests/mo
- ✓Auto cost routing
- ✓Savings dashboard
- ✓Community support
Pro
- ✓1M requests/mo
- ✓Cost analytics + export
- ✓Automatic failover
- ✓Email support
Team
- ✓5M requests/mo
- ✓Custom routing rules
- ✓Team API keys + roles
- ✓Priority support
GST-compliant invoices for Indian customers. Cancel anytime. Refunds per our refund policy.
FAQ
Do I have to change my code?
Just the base URL and your API key. The endpoint is OpenAI-compatible, so the OpenAI SDK, LangChain, LlamaIndex and the Vercel AI SDK all work unchanged.
How do you decide which model to use?
Each request is scored for difficulty and routed to the cheapest model that clears the required quality tier. You can pin a tier with a `quality` field, or force a specific model.
Are the savings real?
Every response includes x-gsw-saved headers and your dashboard tallies actual rupees/dollars saved versus calling a premium model directly. Nothing is estimated after the fact.
What happens if a provider goes down?
Pro and Team plans fail over automatically to the next-best model that still meets your quality bar.
Can I get GST invoices?
Yes — add your GSTIN at checkout and every invoice is tax-compliant for Indian businesses.