---
format: "aidr-story-markdown/v1"
id: "025c2854515a6aae1ae491e56772d1874dfd8c56d3625162440f8543d2ef837f"
canonical_url: "https://aidr.today/025c2854?lang=en"
title: "DeepSeek Launches V4.1 Flash Internal Beta With Native Multimodal Support"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-08T08:37:42.000Z"
category: "Releases"
topics: ["deepseek","releases","v41","multimodal","beta","api","llm","inference"]
source_urls: ["https://huggingnews.com/ai/deepseek-launches-v41-flash-internal-beta-with-native-multimodal-support-7f9f116b","https://x.com/MaxForAI/status/2097229032819691627","https://x.com/gpuhell/status/2097234496202621055","https://x.com/jiqizhixin/status/2097236947030704524","https://x.com/kimmonismus/status/2097286327909675477","https://x.com/zoldener/status/2097354270060187878","https://x.com/plotarmordev/status/2097247035099640216","https://huggingnews.com/ai/update-deepseek-launches-v41-flash-api-beta-with-native-multimodal-archi-2cc897dd"]
summary: "The updated architecture provides faster processing speeds and reduced costs for developers currently in the testing group. This intermediate version, known as V4.1 Flash, is now in internal beta and requires API users to set the model name to deepseek-v4.1-flash-expires-on-0910. The release introduces native multimodal support while maintaining the existing base URL for all requests. Pricing for the trial version remains identical to the current deepseek-v4-flash. DeepSeek has limited access to 20 concurrent requests per account for the duration of the internal test."
---

# DeepSeek Launches V4\.1 Flash Internal Beta With Native Multimodal Support

> [Open the canonical story](<https://aidr.today/025c2854?lang=en>)

**Published:** 2026-09-08T08:37:42.000Z
**Category:** Releases
**Topics:** deepseek, releases, v41, multimodal, beta, api, llm, inference

## Summary

The updated architecture provides faster processing speeds and reduced costs for developers currently in the testing group\. This intermediate version, known as V4\.1 Flash, is now in internal beta and requires API users to set the model name to deepseek\-v4\.1\-flash\-expires\-on\-0910\. The release introduces native multimodal support while maintaining the existing base URL for all requests\. Pricing for the trial version remains identical to the current deepseek\-v4\-flash\. DeepSeek has limited access to 20 concurrent requests per account for the duration of the internal test\.

## Sources

- [Story source](<https://huggingnews.com/ai/deepseek-launches-v41-flash-internal-beta-with-native-multimodal-support-7f9f116b>)
- [Story source](<https://x.com/MaxForAI/status/2097229032819691627>)
- [Supporting source](<https://x.com/gpuhell/status/2097234496202621055>)
- [Supporting source](<https://x.com/jiqizhixin/status/2097236947030704524>)
- [Supporting source](<https://x.com/kimmonismus/status/2097286327909675477>)
- [Supporting source](<https://x.com/zoldener/status/2097354270060187878>)
- [Supporting source](<https://x.com/plotarmordev/status/2097247035099640216>)
- [Story source](<https://huggingnews.com/ai/update-deepseek-launches-v41-flash-api-beta-with-native-multimodal-archi-2cc897dd>)