Model pricing

DeepSeek · Listed Jul 31, 2026 · 37 providers

DeepSeek V4 Flash 0731 API pricing

Calculate
Tool UseReasoningCachingStructured Output
Official pricing
—
Not reported
Lowest input
$0.021
Relace
Context
1.3M

Compare provider pricing

Compare provider pricing per 1 million tokens: input on the horizontal axis and output on the vertical axis. Each grid step is a tenfold change. Outlying pricing is omitted from this chart.

Base pricing

28

Pricing for each hosting provider. Published cache write, batch, request, search, image and audio rates appear in the same row, with units shown beside each amount. Input, output and cache-read pricing is in USD per 1 million tokens. Speed is output tokens per second. Uptime is reported availability. Newest pricing check Sep 28, 2026.

DeepSeek V4 Flash 0731 pricing, speed and uptime by provider
ProviderInputOutputCache readBlendUptimeActions
AtlasCloudfp4$0.44$1.32$0.028$0.505599.3%
Baidufp8$0.44$1.32$0.014$0.5003100.0%
Cloudflare$0.44$1.32$0.014$0.5003100.0%
Novitafp8$0.4092$1.2276$0.026$0.4701100.0%
Alibaba$0.352$1.056$0.0352$0.409299.4%
NextBitfp8$0.352$1.056$0.012$0.400599.9%
Phala$0.308$0.924$0.0196$0.353898.8%
GMICloudfp8$0.286$0.858$0.0091$0.325299.8%
SiliconFlowfp8$0.22$0.66$0.028$0.25899.6%
Reka$0.088$0.528$0.0056$0.167199.9%
Morphbf16$0.142$0.3996$0.0359$0.166698.9%
Venice$0.175$0.35$0.035$0.166399.7%
Cohere$0.14$0.28$0.07$0.148899.5%
COCoreWeavefp8$0.13$0.28$0.07$0.145100.0%
Parasailfp8$0.14$0.28$0.05$0.141399.8%
Together$0.14$0.28$0.03$0.133899.8%
BaseTenfp8$0.13$0.26$0.028$0.1243100.0%
Wafer$0.059$0.35$0.0372$0.123699.9%
SASail Research$0.0225$0.42$0.012$0.117999.7%
OPOpenInferencefp8$0.03$0.40$0.008$0.1142100.0%
DigitalOcean$0.119$0.238$0.0238$0.1131100.0%
Relacefp4$0.021$0.32$0.016$0.093999.8%
Inceptronfp4$0.039$0.2712$0.03$0.093799.9%
MAMakora$0.09$0.195$0.0196$0.089999.0%
SASail Researchfp4$0.0215$0.30$0.014$0.088399.7%
DeepInfrafp8$0.06$0.18$0.015$0.073199.7%
StreamLakefp8$0.044$0.132$0.0014$0.0599.8%
MAMancer 2fp8$0.20$0.60——99.6%

Provider pricing

9

Additional pricing published for this model, including LMSpeed provider feeds. A published listing is not an independent endorsement. Input, output and cache-read pricing is in USD per 1 million tokens. Speed is output tokens per second. Uptime is reported availability.

Amounts are in USD. Hover or tap an underlined amount to see the LMSpeed pricing calculation.

DeepSeek V4 Flash 0731 pricing, speed and uptime by provider
ProviderInputOutputCache readBlendSpeedLatencyUptimeL1L2DRModel IDActions
Elysiver API$0.6796——21.8%100%—35deepseek-v4-flash-0731
KFCV50$0.3801——99.9%100%—24deepseek-v4-flash-0731
向量引擎$0.2337——99.9%100%—11deepseek-v4-flash-0731
HUHuan666 API$0.2056——99.8%100%—20deepseek-v4-flash-0731
GPGPTPlus5 API$0.1209——99.7%100%—19deepseek-v4-flash-0731
iTokens$0.106474.1 tok/s2701 ms98.9%98%0%—deepseek/deepseek-v4-flash-0731
AIAI发财网————99.5%100%—38deepseek-ai/deepseek-v4-flash-0731
MIX API————99.6%100%—10deepseek-ai/deepseek-v4-flash-0731
WOWONG公益站————99.8%100%——deepseek-ai/deepseek-v4-flash-0731

DR is the Ahrefs domain rating of the provider site, from 0 to 100. Domain age is when that site was registered. These describe the public footprint; they do not show whether the provider will keep operating. Listings under a domain rating of 10 are omitted.

Questions about DeepSeek V4 Flash 0731 pricing