DeepSeek V4.1 Flash vs DeepSeek V4 Flash 0731.
model vs model · prices as of
DeepSeek V4 Flash 0731 takes 1 of 5 rounds against DeepSeek V4.1 Flash. It is also the cheaper of the two to run, at $0.22 per million tokens against $1.05.
DeepSeek V4.1 Flash
$1.05/M tokens
DeepSeek list price, nothing below it is accounted for · $0.126 per 1,000 pages
1M context · tool calling · reads images · open weights
DeepSeek V4 Flash 0731
$0.22/M tokens
cheapest we can explain, at OpenRouter · $0.03 per 1,000 pages
1M context · tool calling · open weights
List price in (lower wins)
$0.15/M
$0.15/M
List price out (lower wins)
$0.60/M
$0.60/M
Cheapest we can explain (lower wins)
none below list
$0.22/M at OpenRouter
Standard price (lower wins)
$1.05/M
$1.05/M
Cost per 1,000 pages (lower wins)
$0.126
$0.03
Context
1M tokens
1M tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
yes
yes
Reads images
yes
no
Reasoning
yes
yes
Released
10 Sept 2026
31 Jul 2026
Providers selling it
9
97
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
no provider to check
not stated
Providers selling both · 8
Kilo Gateway$1.05 / $0.22
Nous Portal$1.05 / $0.22
OpenRouter$1.05 / $0.22
TrustedRouter$1.11 / $0.39
LLMTR$1.05 / $0.94
DeepSeek$1.05 / $1.05
Eden AI$1.05 / $1.05
Fireworks AI$1.32 / $1.32
DeepSeek V4.1 Flash then DeepSeek V4 Flash 0731, per million tokens
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- DeepSeek V4 Flash 0731above.dev$0.24 / $0.73 $0.17 / $0.6620% cheaper ·
- DeepSeek V4 Flash 0731
Cortecs$0.14 / $0.29 $0.09 / $0.1834% cheaper · - DeepSeek V4 Flash 0731
GMI Cloud$0.09 / $0.18 $0.29 / $0.86277% dearer · - DeepSeek V4 Flash 0731
Inceptron$0.11 / $0.29 $0.05 / $0.1744% cheaper · - DeepSeek V4 Flash 0731
Inceptron$0.11 / $0.29 $0.05 / $0.1744% cheaper · - DeepSeek V4 Flash 0731
io.net Intelligence$0.23 / $0.73 $0.21 / $0.5913% cheaper · - DeepSeek V4 Flash 0731
Kilo Gateway$0.05 / $0.16 $0.04 / $0.1029% cheaper · - DeepSeek V4 Flash 0731
Mancer$0.17 / $0.50 $0.20 / $0.6021% dearer · - DeepSeek V4 Flash 0731
DeepSeekDeepSeek's list price, in and out per million tokens$0.20 / $0.40 $0.15 / $0.605% dearer · - DeepSeek V4 Flash 0731
Morph$0.12 / $0.35 $0.14 / $0.4015% dearer · - DeepSeek V4 Flash 0731
Nous Portal$0.04 / $0.13 $0.04 / $0.1011% cheaper · - DeepSeek V4 Flash 0731
OpenInference$0.05 / $0.16 $0.04 / $0.1029% cheaper · - DeepSeek V4 Flash 0731
OpenRouter$0.05 / $0.16 $0.04 / $0.1029% cheaper · - DeepSeek V4 Flash 0731
Relace$0.07 / $0.18 $0.06 / $0.1220% cheaper · - DeepSeek V4 Flash 0731
Requesty$0.28 / $0.56 $0.09 / $0.1868% cheaper · - DeepSeek V4 Flash 0731
Sail Research$0.07 / $0.30 $0.07 / $0.3414% dearer · - DeepSeek V4 Flash 0731
StreamLake$0.09 / $0.26 $0.06 / $0.1735% cheaper · - DeepSeek V4 Flash 0731
DeepInfra$0.06 / $0.18 $0.09 / $0.1825% dearer · - DeepSeek V4 Flash 0731
DeepSeek$0.14 / $0.28 $0.15 / $0.6050% dearer · - DeepSeek V4 Flash 0731
Merge Gateway$0.22 / $0.66 $0.14 / $0.2847% cheaper · - DeepSeek V4 Flash 0731
Ofox$0.44 / $1.32 $0.19 / $0.5159% cheaper · - DeepSeek V4 Flash 0731
Zenifra$2.40 / $6.90 $2.20 / $6.606% cheaper ·
Frequently asked
- Which is cheaper, DeepSeek V4.1 Flash or DeepSeek V4 Flash 0731?
- DeepSeek V4 Flash 0731, at $0.22 per million tokens against $1.05 for DeepSeek V4.1 Flash, three parts input to one part output, read on 16 Sept 2026.
- Where is each one cheapest?
- DeepSeek V4.1 Flash: nobody goes below the maker's own price with a reason we can point at, so $1.05 is the number to beat. DeepSeek V4 Flash 0731: $0.22 at OpenRouter.
- Can I buy both from one provider?
- Yes. 8 providers sell both: Kilo Gateway, Nous Portal, OpenRouter, TrustedRouter, LLMTR, DeepSeek, and more. The cheapest of them for the two together is Kilo Gateway.
- Which holds more context?
- Both hold 1M tokens in one call.
Prices exclude tax and are per million tokens, read 16 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.