Availability as of 2 Nov 2026
DeepSeek
DeepSeek V4.1 Flash 1M
DeepSeek V4.1 Flash 1M is an open-weight vision and language model for application builders. Writing and explaining code for development workflows.
The 1017 release, served with its full 1M context window.
deepseek-v4.1-flash-1m- Input / output per 1M
- ₹15 / ₹60
- Hosting
- India‑hosted
- Context
- 1M
- Modalities
- text, image
What can I build with DeepSeek V4.1 Flash 1M?
- Writing and explaining code for development workflows.
- Agent workflows that use model-supported tools.
- Working through questions that need multi-step reasoning.
- Understanding images alongside text prompts.
Plan the integration with the API quickstart, compare rupee pricing and explore applications for your team.
How do I make a request?
Use deepseek-v4.1-flash-1m as the model ID with your IndicStack API key.
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="deepseek-v4.1-flash-1m",
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: "deepseek-v4.1-flash-1m",
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": "deepseek-v4.1-flash-1m",
"messages": [{"role": "user", "content": "Explain what an API is."}]
}'
Questions about DeepSeek V4.1 Flash 1M
Inputs, hosting and access for this model.
Discuss your requirementsWhich modalities does DeepSeek V4.1 Flash 1M support?
DeepSeek V4.1 Flash 1M supports text, image. Choose the request format appropriate to these inputs when planning your application.
Where is DeepSeek V4.1 Flash 1M hosted?
DeepSeek V4.1 Flash 1M is labelled India‑hosted, with inference on GPUs in India.
What is DeepSeek V4.1 Flash 1M best suited for?
DeepSeek V4.1 Flash 1M: Writing and explaining code for development workflows. Agent workflows that use model-supported tools. Working through questions that need multi-step reasoning. Understanding images alongside text prompts.
How much does DeepSeek V4.1 Flash 1M cost?
DeepSeek V4.1 Flash 1M costs ₹15 per 1M input tokens and ₹60 per 1M output tokens, before GST.
What is the served context for DeepSeek V4.1 Flash 1M?
DeepSeek V4.1 Flash 1M has a confirmed served 1M context window. This is the 1017 release with the full 1M window.
How do I call DeepSeek V4.1 Flash 1M from my application?
Set the model field to deepseek-v4.1-flash-1m with the IndicStack base URL and your API key. The code tabs on this page show requests for DeepSeek V4.1 Flash 1M.
Build with DeepSeek V4.1 Flash 1M.
Review the model capabilities and API integration before your first request.