DeepSeek V4 Flash 0731 pricing.
prices as of · 97 providers · 121 prices
DeepSeek V4 Flash 0731 holds 1M tokens of context and has a reasoning mode. Open weights, so anyone may host it, which is why the prices below differ so much.
DeepSeek V4 Flash 0731 costs $0.15 in and $0.60 out per million tokens from DeepSeek; the cheapest price we can explain is $0.22 at OpenRouter, checked 16 Sept 2026.
DeepSeek list price
$1.05/M tokens
$0.15 in · $0.60 out
read · 70% below the market median
Cheapest price we can explain
$0.22/M tokens
$0.04 in · $0.10 out · 79% under list
OpenRouterread
What it costs for your work
DeepSeek list price
$0.126a month
cheapest we can explain · OpenRouter
$0.03a month
difference
$0.096saved
A page is about 600 tokens in and 60 out, a support reply 200 in and 300 out, an email 150 in and 250 out. Nothing else is counted: no cache discount, no batch rate, no free tier.
Every provider selling DeepSeek V4 Flash 0731
Four groups, decided by the price and by what the provider publishes about it. Prices are per million tokens, and the share is that row against DeepSeek's price.
The maker's list price
1 priceWhat the lab that trained the model charges on its own API.
DeepSeekThe price DeepSeek charges for the model it trained. Every row below is measured against it.
$0.15 / $0.60in / out per M
1.00×of list price
Cheaper, and we know why
63 pricesBelow list, with a published reason: hosting the open weights, a regional price list, credits, a stated discount.
- OpenRouter
Routes to a host serving the open weights; precision not disclosed.
1.3M context hereOpenRouter ↗$0.04 / $0.10in / out per M
0.21×of list price
Kilo GatewayRoutes to a host serving the open weights; precision not disclosed.
1M context hereKilo Gateway ↗$0.04 / $0.10in / out per M
0.21×of list price
OpenInferenceServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
1M context herefp8 precision$0.04 / $0.10in / out per M
0.21×of list price
Nous PortalResells OpenRouter's catalog at 0.80× the listed price, funded by a subscription whose credits carry a 10% bonus.
1.3M context hereNous Portal ↗$0.04 / $0.10in / out per M
0.21×of list price
LLM GatewayRoutes to a host serving the open weights; precision not disclosed.
1M context hereLLM Gateway ↗$0.05 / $0.10in / out per M
0.24×of list price
RelaceServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
1M context herefp4 precision$0.06 / $0.12in / out per M
0.29×of list price
CrofServes the open weights at Q8_0, a lower precision than the maker's, so not quite the same product.
Q8_0 precisionCrof ↗$0.07 / $0.10in / out per M
0.30×of list price
UnoRouterHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.06 / $0.13in / out per M
0.30×of list price
- Crof
Hosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.08 / $0.10in / out per M
0.32×of list price
StreamLakeServes the open weights at fp8, a lower precision than the maker's, so not quite the same product.
1M context herefp8 precision$0.06 / $0.17in / out per M
0.33×of list price
$0.07 / $0.14in / out per M
0.33×of list price
TrustedRouterRoutes to a host serving the open weights; precision not disclosed.
1M context hereTrustedRouter ↗$0.07 / $0.18in / out per M
0.37×of list price
AvianHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.08 / $0.16in / out per M
0.38×of list price
RequestyRoutes to a host serving the open weights; precision not disclosed.
1M context hereRequesty ↗$0.09 / $0.18in / out per M
0.43×of list price
DeepInfraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
1M context hereDeepInfra ↗$0.09 / $0.18in / out per M
0.43×of list price
- DeepInfra
Serves the open weights at fp8, a lower precision than the maker's, so not quite the same product.
$0.09 / $0.18in / out per M
0.43×of list price
FastRouterRoutes to a host serving the open weights; precision not disclosed.
1M context hereFastRouter ↗$0.09 / $0.18in / out per M
0.43×of list price
$0.09 / $0.18in / out per M
0.44×of list price
MakoraHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.09 / $0.20in / out per M
0.44×of list price
TokenGoHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.20in / out per M
0.47×of list price
ModelisHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
$0.10 / $0.20in / out per M
0.47×of list price
DigitalOcean GradientHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
1M context hereDigitalOcean Gradient ↗$0.08 / $0.25in / out per M
0.47×of list price
WaferHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
1M context here$0.10 / $0.25in / out per M
0.52×of list price
GMI CloudHosts the open weights on its own servers, so the price is its own, not a resale. Precision not disclosed.
1M context hereGMI Cloud ↗$0.11 / $0.22in / out per M
0.53×of list price
Sail ResearchServes the open weights at fp4, a lower precision than the maker's, so not quite the same product.
1M context herefp4 precision$0.07 / $0.34in / out per M
0.54×of list price
showing the 25 cheapest of 63 · every row in the open dataset
Same price as the maker
41 pricesThe same price the maker charges, sold by someone else.
NVIDIA buildNVIDIA build's catalog shows no price for this row, so there is nothing to compare.
$0 / $0in / out per M
0.00×of list price
$0.15 / $0.25in / out per M
0.67×of list price
OrcaRouterThe same price DeepSeek charges.
$0.15 / $0.29in / out per M
0.70×of list price
VivgridThe same price DeepSeek charges.
$0.15 / $0.30in / out per M
0.71×of list price
- routing.run
The same price DeepSeek charges.
$0.15 / $0.40in / out per M
0.81×of list price
$0.17 / $0.35in / out per M
0.82×of list price
GreenPT6% above DeepSeek's price.
$0.16 / $0.40in / out per M
0.84×of list price
$0.17 / $0.43in / out per M
0.89×of list price
Charm Hyper33% above DeepSeek's price.
$0.20 / $0.40in / out per M
0.95×of list price
$0.20 / $0.40in / out per M
0.95×of list price
$0.20 / $0.40in / out per M
0.95×of list price
OpenCode GoThe same price DeepSeek charges.
$0.15 / $0.60in / out per M
1.00×of list price
- TensorX
67% above DeepSeek's price.
1M context here$0.25 / $0.30in / out per M
1.00×of list price
$0.25 / $0.30in / out per M
1.00×of list price
$0.19 / $0.51in / out per M
1.03×of list price
$0.19 / $0.51in / out per M
1.03×of list price
$0.19 / $0.51in / out per M
1.03×of list price
- above.dev
10% above DeepSeek's price.
$0.17 / $0.66in / out per M
1.10×of list price
$0.21 / $0.59in / out per M
1.17×of list price
$0.23 / $0.62in / out per M
1.25×of list price
- Ollama Cloud
47% above DeepSeek's price.
1M context here$0.22 / $0.66in / out per M
1.26×of list price
- Ollama Cloud
47% above DeepSeek's price.
1M context here$0.22 / $0.66in / out per M
1.26×of list price
$0.22 / $0.66in / out per M
1.26×of list price
$0.22 / $0.66in / out per M
1.26×of list price
$0.29 / $0.86in / out per M
1.63×of list price
showing the 25 cheapest of 41 · every row in the open dataset
Cheaper, and nobody says why
8 prices · never rankedBelow list on a closed model with nothing to account for it. Shown, never ranked, never a pick.
InceptronWe could not read this provider's prices reliably, so the row is listed but never ranked.
1M context here$0.05 / $0.17in / out per M
0.32×of list price
- Inceptron
We could not read this provider's prices reliably, so the row is listed but never ranked.
1M context herefp4 precision$0.05 / $0.17in / out per M
0.32×of list price
AmbientWe could not read this provider's prices reliably, so the row is listed but never ranked.
1M context hereAmbient ↗$0.08 / $0.18in / out per M
0.40×of list price
$0.10 / $0.20in / out per M
0.48×of list price
FeatherlessWe could not read this provider's prices reliably, so the row is listed but never ranked.
262k context hereFeatherless ↗$0.14 / $0.28in / out per M
0.67×of list price
MancerWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.20 / $0.60in / out per M
1.14×of list price
KenariWe could not read this provider's prices reliably, so the row is listed but never ranked.
$0.28 / $0.55in / out per M
1.31×of list price
- Mancer
We could not read this provider's prices reliably, so the row is listed but never ranked.
$76,000 / $200,000in / out per M
407619.05×of list price
Given away with limits
8 free tiers · never rankedThese providers give DeepSeek V4 Flash 0731 away inside a quota of their own. A limit is not a price, so none of them counts as cheapest here or anywhere else on the site.
Alibaba Token Plan
SenseNova (China)
Pendra
InferX- SCNet Token Plan
Volcengine Ark Coding Plan
NaN
Alibaba Token Plan (China)
Frequently asked
- Who sells DeepSeek V4 Flash 0731 cheapest?
- OpenRouter, at $0.04 in and $0.10 out per million tokens, read on 16 Sept 2026. Routes to a host serving the open weights; precision not disclosed.
- Is DeepSeek V4 Flash 0731 open weights?
- Yes. DeepSeek publishes the weights, so anyone may host DeepSeek V4 Flash 0731, which is why 97 providers sell it and why their prices differ so much.
- How much context does DeepSeek V4 Flash 0731 hold?
- 1,000,000 tokens in one call, which is about 1M, and it can call your own functions.
- How does DeepSeek V4 Flash 0731 compare with the rest of the market?
- At $1.05 per million tokens, DeepSeek's price is 70% below the $3.55 median across the 337 text models we track.