# DeepSeek V4.1 Flash: 552B open-weights speedster that beats V4 Pro at a quarter of the cost

> DeepSeek V4.1 Flash is a 552B open-weights MoE with 8B/16B active params, 1M context and native vision – beating V4 Pro on agentic benchmarks at roughly a quarter of the price. Full pricing, benchmarks vs GPT-6 Astra, Claude Fable 5.1 and GLM 5.3, plus what it means for local AI.

*Source: https://velstech.net/deepseek-v4-1-flash · Updated: 2026-09-11 · Category: AI · Tags: LLM, DeepSeek, Benchmarks, AI News, Agents, Open Weights*

*Markdown version of [DeepSeek V4.1 Flash: 552B open-weights speedster that beats V4 Pro at a quarter of the cost](https://velstech.net/deepseek-v4-1-flash). [Read the full guide with interactive tools](https://velstech.net/deepseek-v4-1-flash).*
*Also as Markdown: [Hindi](https://velstech.net/deepseek-v4-1-flash.hi.md) · [Tamil](https://velstech.net/deepseek-v4-1-flash.ta.md).*

---

DeepSeek waited barely a month after the V4 generation to change the subject.
On September 10, 2026 the lab introduced **DeepSeek-V4.1-Flash** –
the smallest model in a brand-new architecture family, with native vision,
a 1M-token context window, and open weights under the MIT license. The headline
claim is deliberately provocative: the cheap "Flash" model now beats the flagship
**V4 Pro on agentic benchmarks**, while costing roughly a quarter of
the price.

I read the launch post, the pricing page, and the technical report's evaluation
tables so you don't have to – and added the two things launch posts never give
you: the full price math (peak vs off-peak, cache hits, migration dates) and an
honest benchmark comparison against today's frontier models –
[GPT-6 Astra](https://velstech.net/gpt-6-astra),
[Claude Fable 5.1](https://velstech.net/claude-fable-5-1), and GLM 5.3.

*Source note:* specs, prices, and scores below come from DeepSeek's
official announcement, the
[official API pricing page](https://api-docs.deepseek.com/quick_start/pricing),
and the model card's evaluation tables (all runs at maximum reasoning effort).
They are vendor-reported numbers, not independent VelsTech benchmarks – and I say
exactly where that matters.

## The short version

- New architecture, tiny active footprint: 552B total parameters,
but only 8B active per token on input (prefill) and 16B on output (decode),
thanks to a Causal Encoder-Decoder design plus compressed sparse attention.

- The Flash beats the Pro: V4.1-Flash tops V4-Pro on Terminal-Bench 2.1
(90.6% vs 87.9%), DeepSWE (74.2% vs 62.7%), AutomationBench (54.8% vs 43.2%),
and several more agentic tests in DeepSeek's own tables.

- It even takes rounds off closed flagships: best-reported scores on
Terminal-Bench 2.1 (90.6%), DeepSWE v1.1 (74.2%), CyberGym (88.1%),
HLE with tools (63.9%), AutomationBench (54.8%), and Codeforces (3471) –
ahead of every rival in DeepSeek's comparison table.

- Pricing is the real masala: $0.30 / $1.20 per million input /
output tokens at peak, halved to $0.15 / $0.60 off-peak, with
cache hits at $0.006 ($0.003 off-peak). That is ~33x cheaper input than
GPT-6 Astra or Claude Fable 5.1.

- Live now as deepseek-flash, with native vision.
Old deepseek-v4-flash names keep working but route to the new model.
V4 Pro was supposed to retire on Sep 14 – DeepSeek has since extended it, so both
stay available for now.

## What V4.1 Flash actually is

V4.1-Flash is the first and smallest member of DeepSeek's V4.1 family – a
multimodal Mixture-of-Experts model that reads images and text and writes text.
It was trained from scratch on 45T tokens, supports thinking and non-thinking
modes plus a dial (reasoning_effort 1–100) that trades cost for accuracy, and
is released open-source (MIT) with weights on Hugging Face.

| Spec | DeepSeek-V4.1-Flash | V4-Flash (prev. gen) | V4-Pro |
| --- | --- | --- | --- |
| Total parameters | 552B | 284B | 1.6T |
| Active per token | 8B prefill / 16B decode | 13B | 49B |
| Architecture | Causal Encoder-Decoder, 40 layers (20+20) | MoE + hybrid attention | MoE |
| Experts | 384 routed + 1 shared, 6 active | – | – |
| Context / max output | 1M / 384K | 1M / 384K | 1M / 384K |
| Vision | Native (DeepSeek-ViT) | Separate exp. variant | Not supported |
| KV cache per token | ~890 bytes (FP4) | ~4x larger | – |
| License | MIT (open weights) | MIT | MIT weights / hosted API |

Two engineering ideas do most of the work. **Compressed Sparse Attention v2**
shares key-value data across layers instead of recomputing it, and
**SWA Bounded Replay** reconstructs short-window attention on the fly
instead of storing it – so the persistent cache shrinks to roughly
**1/4 of V4-Flash in HBM and 1/8 on SSD**, and ~1/437th of the original V1.
For agent workloads that re-read huge contexts all day, that is where the money goes.

## Price details: the full math

DeepSeek kept peak/off-peak pricing and passed the efficiency savings straight to
the rate card. New prices took effect September 10, 2026. Peak hours are
**01:00–04:00 and 06:00–10:00 UTC, Monday–Friday** – everything else
is off-peak at exactly half price.

| Per 1M tokens | V4.1 Flash peak | V4.1 Flash off-peak | V4 Pro peak |
| --- | --- | --- | --- |
| Input, cache miss | $0.30 | $0.15 | $1.32 |
| Input, cache hit | $0.006 | $0.003 | $0.044 |
| Output | $1.20 | $0.60 | $3.96 |

Three things worth noticing. First, the **cache-hit discount is 50x**:
repeated system prompts, repo context, and tool definitions cost $0.006/MTok instead
of $0.30. Agents that reuse context – which is nearly all of them – get dramatically
cheaper than the sticker price suggests. Second, V4.1-Flash is
**~4.4x cheaper than V4 Pro on input and ~3.3x on output** at peak, and
the gap doubles off-peak. Third, the migration is automatic: set the model to
`deepseek-flash`; legacy `deepseek-v4-flash` and
`deepseek-v4-flash-vision-exp` names now route to V4.1-Flash at Flash rates.

One correction to the launch post: it said all `deepseek-v4-pro` traffic
would move to Flash from 04:00 UTC on September 14. DeepSeek's pricing page now says
**V4 Pro stays available with unchanged billing** after that date – so
treat the "Pro is phased out" line as superseded. Concurrency limits are 2500 for
Flash vs 500 for Pro, another quiet reason to default to Flash.

## Benchmarks vs the frontier: where Flash wins and where it doesn't

The table below is DeepSeek's own comparison (maximum reasoning effort,
temperature 1.0 / top_p 0.95, DeepSeek Harness minimal mode for code agents).
Rival columns are Opus-5.0, GPT-5.6 Sol, K3, GLM-5.3, V4-Pro, and V4-Flash.
Read it as "DeepSeek's best foot forward" – harness and effort settings favor the
home team, and independent reruns will follow.

| Benchmark | V4.1 Flash | Best rival in table | Verdict |
| --- | --- | --- | --- |
| Terminal-Bench 2.1 (agentic terminal) | 90.6% | 89.1% (Opus-5.0) | Flash leads |
| DeepSWE v1.1 (software engineering) | 74.2% | 74.0% (Opus-5.0) | Flash leads |
| CyberGym | 88.1% | 84.5% (Sol / GLM-5.3) | Flash leads |
| HLE with tools | 63.9% | 63.6% (Opus-5.0) | Flash leads |
| AutomationBench (office workflows) | 54.8% | 50.3% (Opus-5.0) | Flash leads clearly |
| Agent's Last Exam | 31.8% | 28.6% (Opus-5.0) | Flash leads |
| Codeforces rating | 3471 | 3348 (V4-Pro) | Flash leads |
| MathArena Apex | 65.6% (tie K3) | 65.6% (K3) | Tied best |
| GPQA Diamond (reasoning) | 90.9% | 94.1% (GPT-5.6 Sol) | Behind flagships |
| HLE, no tools | 36.8% | 56.3% (Opus-5.0) | Behind – big gap |
| Terminal-Bench 4.0 | 31.2% | 51.8% (Opus-5.0) | Behind newest harness |
| SEC-Bench Pro | 62.8% | 74.3% (GPT-5.6 Sol) | Behind |
| ExploitGym | 15.3% | 33.7% (GPT-5.6 Sol) | Behind |
| ProgramBench / NL2Repo | 20.3% / 64.0% | 37.0% / 75.3% (Opus-5.0) | Behind |

The pattern is consistent: **V4.1-Flash dominates the "do long multi-step work"
benches** – terminal agents, repo-scale coding, automation, tool-using exams –
while trailing the biggest closed models on **closed-book reasoning**
(HLE without tools) and the very newest harnesses (Terminal-Bench 4.0, SEC-Bench).
Against its own family the story is unambiguous: it beats V4-Pro on nearly every
agentic row (TB 2.1, DeepSWE, CyberGym, HLE+tools, AutomationBench, Agent's Last Exam)
and on base-model coding (HumanEval 79.4%, BigCodeBench 60.6%).

How does this relate to the newest flagships on this site?
[GPT-6 Astra](https://velstech.net/gpt-6-astra) (ARC-AGI-3 99.9%, OSWorld 2.0 72.6%,
Terminal-Bench 4.0 57.9%) and
[Claude Fable 5.1](https://velstech.net/claude-fable-5-1) (Terminal-Bench 4.0 55.8%,
HLE with tools 65.0%) still lead on their strongest harnesses – but those numbers come
from different labs, different harnesses, and different dates, so treat cross-vendor
comparisons as directional, not a controlled race. The fair summary: Flash is the first
open-weights model that looks genuinely competitive with flagships on *agent*
work rather than just chat.

## Frontier price war: Flash vs everyone

Benchmarks are only half the masala. Here is what the same work costs per million
tokens (standard/peak rates; verify each vendor's page before committing):

| Model | Input / 1M | Output / 1M | Cache read / 1M |
| --- | --- | --- | --- |
| DeepSeek V4.1 Flash (off-peak) | $0.15 | $0.60 | $0.003 |
| DeepSeek V4.1 Flash (peak) | $0.30 | $1.20 | $0.006 |
| DeepSeek V4 Pro (peak) | $1.32 | $3.96 | $0.044 |
| GLM-5.3 | $1.40 | $4.40 | $0.26 |
| Gemini 2.5 Pro (≤200K) | $1.25 | $10.00 | $0.125 |
| GPT-5.6 Sol | $4.00 | $20.00 | $0.40 |
| GPT-6 Astra | $10.00 | $50.00 | $1.00 |
| Claude Fable 5.1 | $10.00 | $50.00 | $0.25 |

Put numbers on a realistic agent workload – say ten requests of 200K input tokens
at 80% cache hits plus 50K output tokens each, at peak rates (all within the 1M
context). On V4.1 Flash that is roughly
(0.4M × $0.30) + (1.6M × $0.006) + (0.5M × $1.20) ≈ **$0.73** in total.
The same workload on a $10/$50 flagship with $1.00 cache reads is roughly
$4.00 + $1.60 + $25.00 ≈ **$30.60** – about **42x more**.
Off-peak halves Flash's bill again to about $0.36. Run that through our
[AI API cost calculator](https://velstech.net/ai-api-cost-calculator) with your own
token mix; the break-even vs self-hosting moves a lot at these prices.

## What this means if you run local AI

The honest answer first: **you are not running 552B at home**. The
safetensors release is ~763B parameters including its sparsely-accessed memory, and
third-party estimates put full-precision serving around 1,160 GB of VRAM at short
context – roughly eighteen 80 GB datacenter cards. DeepSeek itself talks about
2,000-GPU-plus-storage deployments for large scale. My 12 GB RX 6800M will not be
downloading this one; see [how much VRAM LLMs
need](https://velstech.net/how-much-vram-for-llm) and the [local-LLM GPU guide](https://velstech.net/best-gpu-for-local-llm) for
what actually fits at home.

What you *can* use: the weights are MIT-licensed, so expect FP8 originals plus
community GGUF quants, Ollama cloud entries (`deepseek-v4.1-flash:cloud`
already exists), and vLLM/SGLang support to mature fast. OpenCode and WorkBuddy
(including CodeBuddy) already list V4.1-Flash support – notable for readers of this
site, since OpenCode-style harnesses are exactly where Flash's benchmark strengths
(DeepSWE, Terminal-Bench, AutomationBench) show up. The practical move for local-AI
folks: keep private/sensitive work on your local 7B–35B models, and route the heavy
agentic jobs you used to hesitate over to a $0.15/MTok API instead of a $10 one.

## How to try it

- Chat: chat.deepseek.com and the DeepSeek app – fastest way to feel the speed.

- API: model="deepseek-flash" on https://api.deepseek.com (OpenAI- and Anthropic-compatible endpoints). Recommended sampling: temperature 1.0, top_p 0.95, 1M context, max_tokens ≥ 256K for long agents.

- Reasoning dial: reasoning_effort 1–100 trades tokens for accuracy – start low for chat, max it for DeepSWE-style tasks.

- Open weights: deepseek-ai/DeepSeek-V4.1-Flash on Hugging Face plus the technical report (PDF).

- Vision: no separate vision model anymore – the same Flash endpoint takes images natively.

## Caveats before you switch everything

- All instruct scores are max-effort runs. Everyday settings (lower reasoning_effort, different scaffolds) will score lower – and cost less. Both halves of that trade-off are the point.

- Harness matters more than usual here. DeepSeek's code-agent numbers use its own minimal harness at 1M context; Claude Code, Codex, and OpenCode scaffolds score a few points differently on the same model (DeepSWE 65–70 vs 74.2 on mini-SWE).

- Closed-book reasoning still belongs to the giants. HLE without tools (36.8% vs 56.3% for Opus-5.0) and GPQA Diamond (90.9% vs 94.1% for GPT-5.6 Sol) show where the 8B-active diet bites.

- Prices move. Peak windows, the V4-Pro extension, and off-peak halves are policy, not physics – re-check the official pricing page before budgeting.

## Bottom line

V4.1-Flash is the rare release that is interesting for two opposite reasons at once.
Architecturally, the encoder-decoder + sparse-attention + replay tricks squeeze a
552B model through an 8B-wide straw – and the KV-cache savings (1/4 the HBM, 1/8 the
SSD) are genuinely new. Economically, it undercuts every flagship by 30–60x while
beating its own Pro sibling where it counts for agent builders. If your workload is
long tool-using sessions with big reused contexts, this is the default to beat right
now – open weights included. If it is closed-book Olympiad reasoning on the newest
harness, keep the flagship subscription warm.

## Sources

- DeepSeek: Introducing DeepSeek-V4.1-Flash

- DeepSeek API Docs: Models & Pricing

- Hugging Face: deepseek-ai/DeepSeek-V4.1-Flash (model card + evaluation tables)

- DeepSeek_V41_Tech_Report.pdf

- VelsTech AI API cost calculator

## FAQ

**What is DeepSeek V4.1 Flash?**

V4.1-Flash is DeepSeek's open-weights (MIT) multimodal MoE model with 552B total parameters but only 8B active on input and 16B on output, a 1M-token context window, and native vision. It is served via the API as deepseek-flash.

**How much does DeepSeek V4.1 Flash cost?**

At peak, $0.30 per million input tokens, $1.20 per million output tokens, and $0.006 per million cache-hit tokens. Off-peak rates are exactly half ($0.15 / $0.60 / $0.003). That is roughly 33x cheaper input than $10-per-million flagships.

**Is V4.1 Flash better than V4 Pro?**

On DeepSeek's own agentic benchmarks, yes: V4.1-Flash beats V4-Pro on Terminal-Bench 2.1 (90.6% vs 87.9%), DeepSWE (74.2% vs 62.7%), and AutomationBench (54.8% vs 43.2%), while costing about a quarter of the price.

**Can I run DeepSeek V4.1 Flash locally?**

Not on consumer hardware. The full release needs on the order of a terabyte of VRAM, so it is a datacenter model. Home users can use the chat app, the cheap API, Ollama cloud entries, or wait for community quantizations – local 7B-35B models still win on privacy and offline use.

---

*VelsTech – technology explained for everyone. Original: https://velstech.net/deepseek-v4-1-flash*