FAQ
Questions about the API, hosting and billing.
Find the operational details for your first request or a client deployment.
Get your API keyAPI access, data handling and costs
Answers from the published product and pricing information.
Discuss your requirementsCan I use my existing OpenAI SDK?
Sign up in the console, create a key, and configure your server's OpenAI SDK with https://api.indicstack.ai/v1 and your IndicStack key.
What will my first workload cost?
Free Trial: free, with ₹2,000 credit for 15 days on any model, 1 request at a time, 20 requests per minute and 1 API key. Unlimited Pro: ₹2,499/month + GST for unlimited tokens on Unlimited models, ₹500 frontier credit/month, 2 requests at once, 60 requests per minute and 1 API key. Unlimited Team: ₹9,999/month + GST for unlimited tokens on Unlimited models, ₹2,500 frontier credit/month, 8 requests at once, 200 requests per minute and up to 10 API keys. Fair use: after very heavy daily use, requests move to a slower queue instead of stopping. On Qwen3.8 27B, pay ₹21 per million input tokens and ₹190 per million output tokens, before 18% GST.
What credit do I get when I sign up?
New accounts receive ₹2,000 in free credit, valid for 15 days. Purchased credit never expires.
How do I choose India‑hosted or Global?
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 when the balance is empty?
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 I separate spend for different clients?
Create a key per client and track spend by key on the dashboard. IndicStack bills you in rupees with GST invoices.
Are my prompts used to train models?
Prompts and completions on India‑hosted models are never used to train models.
Can you deploy a model for my team?
Dedicated GPU deployments in India, specialist models, custom agents, RAG and AI consulting are available through our team.
What are the current pay-as-you-go rates?
On Qwen3.8 27B, pay ₹21 per million input tokens and ₹190 per million output tokens, before 18% GST. Other live models have their own rates in the per-model table; Decider is billed only for input tokens.
How much is 10M input and 2M output tokens?
That workload on Qwen3.8 27B costs ₹590.00 before GST, or ₹696.20 including GST.
What do Pro and Team include?
Unlimited Pro: ₹2,499/month + GST for unlimited tokens on Unlimited models, ₹500 frontier credit/month, 2 requests at once, 60 requests per minute and 1 API key. Unlimited Team: ₹9,999/month + GST for unlimited tokens on Unlimited models, ₹2,500 frontier credit/month, 8 requests at once, 200 requests per minute and up to 10 API keys. Fair use: after very heavy daily use, requests move to a slower queue instead of stopping. Unlimited models: Qwen3.8-27B, DeepSeek V4.1 Flash, GLM-5.3 Flash, Gemma 4 31B IT, Gemma 4 26B A4B IT, Nemotron 3.5 Super VL 120B A12B. Frontier models: DeepSeek V4.1 Flash 1M, GLM-5.3 Flash 1M, GLM-5.3, Perplexity Decider v1.1 (27B). Frontier credit resets monthly and does not roll over. After your frontier credit, frontier models use your pay-as-you-go wallet.
Is GST included in the displayed prices?
Displayed prices are before 18% GST. You receive GST invoices for your finance team to file and claim eligible input tax credit.
Does prepaid credit expire?
New accounts receive ₹2,000 in free credit, valid for 15 days. Purchased credit never expires. Frontier credit resets monthly and does not roll over.
Will calls keep running after credit reaches zero?
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.
How are dedicated deployments priced?
On-request models are deployed on GPUs in India for your workload and priced per deployment. Contact us with your application requirements.
Can I track costs separately for each client?
Yes. Create a key for each client and use the dashboard's spend-by-key view to track the corresponding usage.
Discuss the requirements for your build.
Tell our team what you need to integrate or deploy.