Shortcut ChatShortcut Chat
Get started

AI model comparison

DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0813

Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.

deepseek logo

DeepSeek

DeepSeek V4.1 Flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture.

Input / 1M
$0.30
Output / 1M
$1.20
Context
1.05M
deepseek logo

DeepSeek

DeepSeek V4 Pro 0813

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek.

Input / 1M
$0.66
Output / 1M
$1.98
Context
1.05M

At a glance

Quick verdict

How the two models stack up on the things people ask about most.

Lower price

deepseek logo

DeepSeek V4.1 Flash

1.9x cheaper for a typical chat

Higher intelligence score

deepseek logo

DeepSeek V4.1 Flash

39.5 vs 36 on Artificial Analysis

Larger context window

Tie

1.05M vs 1.05M tokens

Newer release

deepseek logo

DeepSeek V4.1 Flash

Released September 10, 2026

Benchmarks

Benchmark scores

Independent scores from Artificial Analysis. Higher is better.

Intelligence index

deepseek logoDeepSeek V4.1 Flash39.5
deepseek logoDeepSeek V4 Pro 081336

Coding index

deepseek logoDeepSeek V4.1 FlashNot available
deepseek logoDeepSeek V4 Pro 081368.8

Agentic index

deepseek logoDeepSeek V4.1 FlashNot available
deepseek logoDeepSeek V4 Pro 081341.3

Pricing

DeepSeek V4.1 Flash vs DeepSeek V4 Pro 0813 API pricing

Per-token API rates. Cheaper option highlighted.

Metricdeepseek logoDeepSeek V4.1 Flashdeepseek logoDeepSeek V4 Pro 0813
Input tokensPer 1M tokens$0.30$0.66
Output tokensPer 1M tokens$1.20$1.98
Cached input (read)Per 1M tokens$0.01$0.02
Cache writePer 1M tokensNot availableNot available

What it costs in practice

Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.

Chat message

2K in, 500 out

deepseek logoDeepSeek V4.1 Flash$1.20
deepseek logoDeepSeek V4 Pro 0813$2.31

Coding task

30K in, 4K out

deepseek logoDeepSeek V4.1 Flash$13.80$4.98 cached
deepseek logoDeepSeek V4 Pro 0813$27.72$8.58 cached

Long document summary

150K in, 2K out

deepseek logoDeepSeek V4.1 Flash$47.40$3.30 cached
deepseek logoDeepSeek V4 Pro 0813$102.96$7.26 cached

Specs

Context window and capabilities

How much each model can read, how much it can write, and what it accepts as input.

Metricdeepseek logoDeepSeek V4.1 Flashdeepseek logoDeepSeek V4 Pro 0813
Context window1.05M tokens1.05M tokens
Max output944K tokens393K tokens
Input typesImage, TextText
Output typesTextText
Reasoning effort levelsMax, High, LowMax, High, Low
Default reasoning effortHighHigh
Release dateSeptember 10, 2026August 12, 2026

Features

Supported features

API features available for each model.

Metricdeepseek logoDeepSeek V4.1 Flashdeepseek logoDeepSeek V4 Pro 0813
Tool callingSupportedSupported
Structured outputsSupportedSupported
JSON modeSupportedSupported
ReasoningSupportedSupported
TemperatureSupportedSupported
Stop sequencesSupportedSupported
Deterministic seedSupportedSupported
Verbosity controlNot supportedNot supported

Our take

DeepSeek V4.1 Flash is 1.9x cheaper for a typical chat. DeepSeek V4.1 Flash scores higher on the Artificial Analysis Intelligence Index (39.5 vs 36). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.

FAQ

Frequently asked questions

Is DeepSeek V4.1 Flash or DeepSeek V4 Pro 0813 cheaper?

DeepSeek V4.1 Flash is cheaper for a typical chat (2K input tokens and 500 output tokens). DeepSeek V4.1 Flash costs $0.30 per 1M input tokens and $1.20 per 1M output tokens, while DeepSeek V4 Pro 0813 costs $0.66 per 1M input tokens and $1.98 per 1M output tokens.

Which has a bigger context window, DeepSeek V4.1 Flash or DeepSeek V4 Pro 0813?

DeepSeek V4.1 Flash supports up to 1.05M tokens of context, compared with 1.05M for DeepSeek V4 Pro 0813.

Is DeepSeek V4.1 Flash smarter than DeepSeek V4 Pro 0813?

On the Artificial Analysis Intelligence Index, DeepSeek V4.1 Flash scores 39.5 and DeepSeek V4 Pro 0813 scores 36, putting DeepSeek V4.1 Flash ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.

Can I use DeepSeek V4.1 Flash and DeepSeek V4 Pro 0813 at the same time?

Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see DeepSeek V4.1 Flash and DeepSeek V4 Pro 0813 answer side by side and keep the better response.

deepseek logodeepseek logo

Why choose? Ask both.

Send one prompt to DeepSeek V4.1 Flash and DeepSeek V4 Pro 0813 at the same time. Compare the answers side by side and keep the best one.

Get startedSee a preview