For agencies
Separate keys. Spend tracked by client.
IndicStack gives agencies an OpenAI-compatible API with per-client keys, spend tracking and rupee billing for client applications.
How do agencies track AI costs per client?
Create a key per client and read spend by key on the dashboard. Use those usage figures to invoice your clients.
- Create a key per client.
Revoke one without touching the rest.
- Track spend by key.
See what each client costs you on one dashboard.
- Invoice from actual usage.
Pass costs through with rupee billing and GST invoices.
- Choose India‑hosted inference when required.
Review the hosting label for the selected model.
Build agents and RAG with our team.
We work with you on agents, RAG and integrations. Rupee billing and GST invoices let you pass costs through cleanly and claim input credit.
Discuss a client project →Related models for your application
Use the API quickstart to connect your application, and check rupee pricing when estimating the workload.
Questions before your first client key
Practical answers for allocating spend, billing clients and reviewing hosting requirements.
Discuss your requirementsHow do I separate one client's AI usage?
Create a key for that client and store it in the client's application. The dashboard tracks spend by API key.
Can I revoke a client key without affecting the rest?
Yes. Keys can be revoked separately, without touching the other keys in the account.
How do I invoice from actual client usage?
Read each client's spend from its API key on the dashboard, then invoice your client from those usage figures. IndicStack bills you in rupees with GST invoices.
What does a client's token workload cost?
On Qwen3.8 27B, pay ₹21 per million input tokens and ₹190 per million output tokens, before 18% GST.
What if a client requires inference in India?
India‑hosted models run on GPUs in India. Global models run outside India on partner infrastructure; check the hosting label for the route you select.
What happens if our shared credit runs out?
Pay-as-you-go calls stop when your prepaid wallet reaches zero. Top up before making further pay-as-you-go calls. Paid packages still include unlimited tokens on Unlimited models.
Can you support our client's security review?
The sub-processor list, data-flow overview and security questionnaire answers are available on request.
Can your team help build the client application?
Our team works with agencies on custom agents, RAG and integrations. A client can also request a dedicated model on GPUs in India.
Start with a key for your first client.
₹2,000 in free credits. Valid for 15 days.