Enterprise DNAEnterprise DNA

Model comparison

DeepSeek V4.1 Flash vs DeepSeek V4 Pro (Thinking)

Price history, scores and specs for both models, line by line. Every value shows where it came from and when we last confirmed it.

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.

17 checked values

Flagship DeepSeek model for coding, reasoning, and agentic work.

0 checked values

Price history

Prices side by side, day by day

Input price history
$0$0.162$0.32420 Sept 202610 Nov 2026
  • DeepSeek V4.1 Flash 38 checked days, 20 Sept 2026 to 10 Nov 2026. Checked 11 Nov 2026 · OpenRouter models API
  • DeepSeek V4 Pro (Thinking) No price history checked yet
Output price history
$0$1.29$2.5920 Sept 202610 Nov 2026
  • DeepSeek V4.1 Flash 38 checked days, 20 Sept 2026 to 10 Nov 2026. Checked 11 Nov 2026 · OpenRouter models API
  • DeepSeek V4 Pro (Thinking) No price history checked yet

Prices are the listed OpenRouter base rates in US dollars. A day we could not confirm is left out of the line, never filled in.

Price

What each one costs now

DeepSeek V4.1 Flash vs DeepSeek V4 Pro (Thinking): What each one costs now
MeasureDeepSeek V4.1 FlashDeepSeek V4 Pro (Thinking)
Input price$0.051 per million tokensChecked OpenRouter models APINot checked yet
Output price$0.567 per million tokensChecked OpenRouter models APINot checked yet

Scores

Benchmarks, with source and date

DeepSeek V4.1 Flash vs DeepSeek V4 Pro (Thinking): Benchmarks, with source and date
MeasureDeepSeek V4.1 FlashDeepSeek V4 Pro (Thinking)
Artificial Analysis Intelligence Index24.7Checked Artificial Analysis via OpenRouterNot checked yet
LMArena text rating (Elo)1,463Checked LMArena (CC-BY-4.0), published 2026-11-09Not checked yet
LMArena web development rating (Elo)1,664Checked LMArena (CC-BY-4.0), published 2026-11-09Not checked yet
LMArena vision rating (Elo)1,279Checked LMArena (CC-BY-4.0), published 2026-11-09Not checked yet

Specs

Context, modalities and tool use

DeepSeek V4.1 Flash vs DeepSeek V4 Pro (Thinking): Context, modalities and tool use
MeasureDeepSeek V4.1 FlashDeepSeek V4 Pro (Thinking)
Context window1,048,576 tokensChecked OpenRouter models APINot checked yet
ReadsText, ImagesChecked OpenRouter models APINot checked yet
WritesTextChecked OpenRouter models APINot checked yet
Tool callingYesChecked OpenRouter models APINot checked yet
Reasoning modeYesChecked OpenRouter models APINot checked yet
Open weightsYesChecked OpenRouter models APINot checked yet
Listed since10 Sept 2026Checked OpenRouter models APINot checked yet

Usage

How much each one is used

DeepSeek V4.1 Flash vs DeepSeek V4 Pro (Thinking): How much each one is used
MeasureDeepSeek V4.1 FlashDeepSeek V4 Pro (Thinking)
Tokens served on OpenRouter in a day2.3T (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)Not checked yet
Requests on OpenRouter in a day76M (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)Not checked yet
Tool calls on OpenRouter in a day20.1M (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)Not checked yet
Token usage, last 7 daysUp 8% on the week before (for 10 Nov 2026)Checked OpenRouter model activity (748 of 748 series)Not checked yet
Tokens served a day on OpenRouter
1.2T4.6T8T19 Sept 202610 Nov 2026

How this works

One link, either order

This link stays the same whichever order you name the two models in, so you can share it as it is. A line appears only when at least one model has a value we confirmed from a source; values we have not confirmed are left out, never guessed. To add a third record of any type, use the open comparison. Read how we check facts.