DeepSeek V4.1 Flash
DeepSeek's V4.1 Flash is a very large text model for writing and answering questions, free to download, and needs powerful servers to run.
Key facts
- Released
- Sep 9, 2026
- What it does
- Text and chat: Writes, answers questions and holds a conversation.Thinks first: Can reason step by step before it answers: slower, but better at maths, code and tricky questions.Sees images: Understands pictures, screenshots and charts you share with it.
View moreView less
- Knowledge cutoff
- May 2025 · the latest events it learned about
- How
- Free to download
- Size
- Parameters: The numbers a model learns during training: a rough measure of its size. Bigger usually means more capable, but slower and pricier to run. 7B means 7 billion.
- Announced as
- “DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression”
From trckr's archive of releases before it started watching. Date and details from Epoch AI's database of AI models (CC BY 4.0).
Price and limits
What developers pay to use it through the API: How developers plug a model into their own apps and pay per use. A model that's "in the API" can be used by programmers, even if it isn't in a chat app yet., per million Tokens: The small chunks of text a model reads and writes, about three-quarters of a word each. Prices and limits are counted in tokens. sent (input) or written back (output), and how much it can take in at once.
- Input
- $0.15
- per million tokensCached: $0.003
- Output
- $0.60
- per million tokens
- Context window: How much a model can keep in mind at once: your question, any files you share and its own replies. Measured in tokens; 1,000 tokens is about 750 words.
- 1.05M tokens
- about 790,000 words
View moreView less
- Longest answer
- 393K tokens (about 290,000 words)
From the lab's own listing on models.dev and OpenRouter, checked .
How it scores
From independent testers, never the lab's own claims.
- Combined test score#19 of 235
- GPT-6 Astra169
- 2GPT-6.1 Sol169
- 18Claude Opus 4.8160
- 19DeepSeek V4.1 Flash159
- 20Gemini 3.8 Flash159
Source: Epoch AI · Epoch Capabilities Index
- Chat answers, by people's votes#31 of 86
- Gemini 4 Carbon1,527
- 2Gemini 4 Argon1,522
- 30GLM-5.21,475
- 31DeepSeek V4.1 Flash1,475
- 32Grok 4.20 Beta 11,475
Source: LMArena · LMArena text, adjusted for style
- Building apps, by people's votes#14 of 85
- Claude Opus 5.51,818
- 2Claude Sonnet 5.51,773
- 13GPT-6 Sol1,674
- 14DeepSeek V4.1 Flash1,664
- 15Kimi K31,657
Source: LMArena · LMArena WebDev
Compare DeepSeek V4.1 Flash with
It came out 27 days after DeepSeek V4 Pro 0813, the lab's previous model.
The details
DeepSeek V4.1 Flash is a 550 billion parameters: Data-centre scale: it runs on many chips (GPUs) at once. Parameters are the numbers a model learns: a rough measure of its size. Language model (LLM): A model trained on huge amounts of text to read and write. The engine behind chatbots like ChatGPT, Claude and Gemini. for question answering and text generation, released as Open weights: The model's files are public, so anyone can download it, run it on their own computer and build on it, usually for free. trckr labels these "Open". with unrestricted use, with its announcement focused on KV cache compression.
Model ID: The exact name developers type to use a model, like gpt-5-mini. New IDs often show up in a lab's systems before the official announcement, which is how trckr spots many releases early.
deepseek/deepseek-v4.1-flash-1017deepseek-flashTimeline
/OpenRouterFirst signal
/DeepSeek APIOfficial
deepseek-flash
Get alerts like this the moment they happen.
From DeepSeek and every other major lab.