# DeepSeek-V4.1-Flash

DeepSeek-V4.1-Flash is a model from DeepSeek, first recorded on 16 Sep 2026; its release date is not established. The context window is 1,048,576 tokens. The maximum output is 393,216 tokens. Pricing is $0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million input tokens and $0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million output tokens.

- Developer: DeepSeek
- Id: deepseek-flash
- Sighting: 2026-09-16T05:20:37.084Z
  - [evidence link](https://models.dev/#deepseek-flash)
- Status: API availability
- Canonical: https://alexgetman.com/models/deepseek/deepseek-flash/

## Questions

### What is the context window of DeepSeek-V4.1-Flash?

The context window is 1,048,576 tokens. The maximum output is 393,216 tokens.

### How much does DeepSeek-V4.1-Flash cost?

Pricing is $0.15 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.30 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million input tokens and $0.60 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $1.20 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million output tokens. Cached input is $0.003 (Off-peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.); $0.006 (Peak: Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday, excluding Chinese public holidays. All other hours are off-peak, including weekends and Chinese public holidays in full.) per million.

### When was DeepSeek-V4.1-Flash released?

Its release date is not established. Signal Forge first recorded it on 16 Sep 2026.

## Evidence links

- [deepseek-pricing](https://api-docs.deepseek.com/quick_start/pricing/?article_id=article_1779470751466_8)
- [deepseek-api](https://api.deepseek.com/models)
- [Artificial Analysis · benchmarks](https://artificialanalysis.ai/models)
- [Hacker News · front page](https://artificialanalysis.ai/models/deepseek-v4-1-flash-1017)
- [Hugging Face · inference providers](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017)
- [models.dev · catalogue](https://models.dev/#DeepSeek-V4.1-Flash-1017)
- [models-dev](https://models.dev/#deepseek-flash)
- [models.dev · catalogue](https://models.dev/#deepseek-v4-1-flash-1017)
- [models.dev · catalogue](https://models.dev/#deepseek-v4.1-flash-1017)
- [models.dev · catalogue](https://models.dev/#morph-dsv41flash-1017)
- [models.dev · catalogue](https://models.dev/#umans-deepseek-v4.1-flash-1017)
- [OpenRouter](https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017)
- [OpenRouter](https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017:batch)
- [Alibaba Model Studio API](https://www.alibabacloud.com/help/en/model-studio/models)
- [DesignArena · website](https://www.designarena.ai/leaderboard/website)

## Signals

- [DeepSeek V4.1 Flash 1017 (Max) enters at 45.1 on the Intelligence Index](https://alexgetman.com/signals/2026/10/19/deepseek-v4-1-flash-1017-max-enters-45-1-intelligence-index/)
- [DeepSeek-V4.1-Flash spotted on models.dev](https://alexgetman.com/signals/2026/10/18/deepseek-v4-1-flash-1017-non-reasoning/)