A key per client
Separate keys per app, environment or client. Spend by key on the dashboard. Revoke one without touching the rest.
Platform
One API, separate client keys and rupee billing.
IndicStack is an OpenAI-compatible API for teams building with open-weight models. Manage per-client keys, request logs and prepaid rupee billing.
How do I connect my application?
Use the IndicStack base URL and your API key with the OpenAI SDK. Choose a live model by its model ID.
qwen38-27b model details
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.indicstack.ai/v1",
api_key=os.environ["INDICSTACK_API_KEY"],
)
response = client.chat.completions.create(
model="qwen38-27b",
messages=[{"role": "user", "content": "Explain what an API is."}],
)
print(response.choices[0].message.content)
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://api.indicstack.ai/v1",
apiKey: process.env.INDICSTACK_API_KEY,
});
const response = await client.chat.completions.create({
model: "qwen38-27b",
messages: [{ role: "user", content: "Explain what an API is." }],
});
console.log(response.choices[0].message.content);
curl https://api.indicstack.ai/v1/chat/completions \
-H "Authorization: Bearer $INDICSTACK_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen38-27b",
"messages": [{"role": "user", "content": "Explain what an API is."}]
}'
Hosting controls
How do I keep inference in India?
- 01
Pick by capability.
Browse models by capability and check the hosting information.
- 02
Choose India‑hosted inference.
Qwen3.8 27B runs on GPUs in India.
- 03
Review your data requirements.
Check the data-flow overview and request compliance documents for your workload.
Building for a regulated client? See how we handle data →
Track access, requests and spend.
Request logs
See model, tokens, time and key for each call.
Prepaid rupee billing
Get GST invoices. Credit you buy never expires, and calls stop at zero.
Team access
Invite members to manage keys and billing together.
Related models for your application
Use the API quickstart to connect your application, and check rupee pricing when estimating the workload.
How the API and console fit together
Integration and operational details for teams moving from a first request to a client application.
Discuss your requirementsWhat changes in my application code?
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.
Can one account track different client applications?
Create separate keys per app, environment or client. Spend by key appears on the dashboard, and one key can be revoked without touching the others.
What can I see in request logs?
Request metadata includes model, tokens, timestamp and API key ID. The dashboard shows spend by model and by API key.
Can I send images or use tools?
Qwen3.8 27B supports image input and tool calling. Capabilities depend on the selected model; review its inputs before integrating.
Where is my model request processed?
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.
How does the credit balance affect API access?
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.
What billing records do I receive?
Billing is in rupees with GST invoices. The dashboard shows credit, spend, requests, tokens and daily spending.
Which documents can our security team review?
The sub-processor list, data-flow overview and security questionnaire answers are available on request.
Connect your application to IndicStack.
Use one API for model access, request logs and rupee billing.