Qwen3-Coder-Next
Global
Focused on code generation and coding-agent workflows.
View model →For developers
Build on open models. Pay in rupees.
IndicStack is an OpenAI-compatible API for developers building with open-weight models, free to start and billed in rupees.
How do I make my first API request?
- 01
Create your account
Free for 15 days on Qwen3.8-27B.
- 02
Create a key
Generate your key in the console.
- 03
Configure the SDK
Set the IndicStack base URL and key on your server.
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."}]
}'
Choose a model for your workload.
Qwen3.8-27B
India‑hosted
Tool calling for agents, with image input and long context.
View model →GLM-5.3
Global
Reasoning and long-document tasks in one model.
View model →Pay per token or choose Pro or Team.
Pay as you go
₹21 input / ₹190 output per 1M tokens on Qwen3.8-27B. Charged from prepaid rupee credit.
Pro
Pro: ₹2,499/month + GST for unlimited Qwen3.8-27B and ₹2,000 credit a month for every other model, 2 requests at once, 60 requests per minute and 1 API key.
Team
Team: ₹9,999/month + GST for unlimited Qwen3.8-27B and ₹8,000 credit a month for every other model, 8 requests at once, 200 requests per minute and up to 10 API keys.
Keep your SDK and frameworks.
Use the OpenAI SDKs for Python and Node.js, or a framework that accepts an OpenAI-compatible base URL: LangChain, LlamaIndex and Vercel AI SDK.
When a customer requires India‑hosted inference, choose Qwen3.8-27B, hosted on GPUs in India.
Read about data handling →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 request
The model ID, request format and credit rules to check before connecting your application.
Discuss your requirementsWhat are the setup steps?
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.
Which model ID should I use first?
Use qwen38-27b for the live Qwen3.8-27B. It supports text, image input, tool calling and 262K context.
Can I test for free?
New accounts can use Qwen3.8-27B free for 15 days. Other models need a prepaid wallet, with a minimum top-up of ₹500. Credit you buy never expires.
What limits apply to Pro and Team?
Pro: ₹2,499/month + GST for unlimited Qwen3.8-27B and ₹2,000 credit a month for every other model, 2 requests at once, 60 requests per minute and 1 API key. Team: ₹9,999/month + GST for unlimited Qwen3.8-27B and ₹8,000 credit a month for every other model, 8 requests at once, 200 requests per minute and up to 10 API keys. Unlimited applies to Qwen3.8-27B, which we host ourselves. It runs within your plan's request limits; when those are reached, further requests wait their turn.
What happens when a request uses the last of my credit?
Pay-as-you-go calls stop when your prepaid wallet reaches zero. Top up before making further pay-as-you-go calls. Pro and Team still include unlimited Qwen3.8-27B.
How should I choose a model for the task?
Compare use cases and inputs in the catalog. Coding, agents, reasoning and vision filters help narrow the selection; check availability before making calls.
Do I need to change SDKs to use India‑hosted inference?
The API uses the OpenAI chat completions format. 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 can I compare per-token cost with a monthly plan?
On Qwen3.8-27B, pay ₹21 per million input tokens and ₹190 per million output tokens, before 18% GST. The pricing calculator estimates a token workload so you can compare it with Pro or Team.
Send your first request.
Create a key, set your base URL and run the quickstart.