# OpenRouter adds DeepSeek V4.1 Flash 1017 model

> OpenRouter now offers DeepSeek V4.1 Flash 1017, a sparse mixture‑of‑experts model with a 1‑million token context window.

Oossa · 2026-10-17 · https://oossa.com/en/openrouter-adds-deepseek-v4-1-flash-1017-model

OpenRouter has added a new model called DeepSeek V4.1 Flash 1017. It is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, provided under the `deepseek-flash` API name. The model uses a sparse mixture‑of‑experts architecture and can handle up to 1,048,576 tokens of context in a single request.

## The facts

- Model name: DeepSeek V4.1 Flash 1017
- Context length: 1,048,576 tokens

## Why it matters

Developers can now build longer‑form AI applications, such as document analysis or extended chat sessions, without breaking the text into pieces.

## Sources & references

1. [New on OpenRouter: DeepSeek: DeepSeek V4.1 Flash 1017](https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017) – OpenRouter API, 2026-10-17

Last updated: 2026-10-17