Skip to content

Compare model prices

Input, output, cached and batch prices, every route and a month of tokens, side by side.

DeepSeek V4 Flash 0731DeepSeek V4.1 Flash

A month of tokens

  • DeepSeek V4 Flash 0731$8.45
  • DeepSeek V4.1 Flash$27.00

100M input and 20M output tokens, list price. Use your own numbers.

Side by side

DeepSeek V4 Flash 0731DeepSeek V4.1 Flash
Input per 1M$0.053$0.15
Output per 1M$0.158$0.6
Cached input$0.0017$0.003
Batch in / outn/a$0.112 / $0.336
Blended (3:1)$0.079$0.262
Context1.31M1M
Routes2925
ReleasedJul 31, 2026Sep 10, 2026
Leadersboard scoren/a3 (#33)

On the price map

$0.03$0.1$0.3$1$3$10$30$100$0.03$0.1$0.3$1$3$10$30$100$300Input $ per 1M tokensOutput $ per 1M tokensxxZZDMOOOOOOOOOOOOOOOOZDGMMDMGDQMGGMMZGGDDGGGGGGGGMOOOZQAQQAQQQAAAQAQxQQAQQAQAAAAQQQQxxxOOOOOOOOOOOOOOOOOAAOMMQQQMGGMQQQQQQQMMMMQQQQQQQMQQQQxMMCZZZZZZZAAAOAOOOOOOOACDDDDDMDDMGGZMOQQQMOOZZQMMQQQQQGGGMMMMMMOOOMQCAOCCOOOOOOMQGGGZMDMMGMMQQQ
Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

DeepSeek V4 Flash 0731

Way to buyIn / out per 1M
StreamLake
fp8 · cached $0.0017
$0.053 / $0.158Same as list
DeepInfra
fp8 · cached $0.015
$0.06 / $0.18+14% vs list
Relace
fp4 · cached $0.016
$0.04 / $0.32+39% vs list
Makora
Default region · cached $0.02
$0.09 / $0.195+47% vs list
Wafer
fast · cached $0.02
$0.08 / $0.35+86% vs list
DigitalOcean
Default region · cached $0.024
$0.119 / $0.238+88% vs list
Baseten
fp8 · cached $0.028
$0.13 / $0.26+105% vs list
Sail Research
fp4 · cached $0.023
$0.038 / $0.55+110% vs list
CoreWeave
fp8 · cached $0.07
$0.13 / $0.28+111% vs list
Cohere
Default region · cached $0.07
$0.14 / $0.28+121% vs list
Nebius
fp8
$0.14 / $0.28+121% vs list
Parasail
fp8 · cached $0.05
$0.14 / $0.28+121% vs list
Together AI
Default region · cached $0.03
$0.14 / $0.28+121% vs list
Reka
fp4 · cached $0.0056
$0.088 / $0.528+150% vs list
Morph
Default region · cached $0.036
$0.142 / $0.4+161% vs list
Venice
Default region · cached $0.035
$0.175 / $0.35+176% vs list
Inceptron
fp4 · cached $0.06
$0.091 / $0.613+179% vs list
OpenInference
fp8 · cached $0.03
$0.14 / $0.7+254% vs list
Mancer 2
fp8
$0.2 / $0.6+279% vs list
Fireworks AI
Default region · cached $0.007
$0.22 / $0.66+317% vs list
SiliconFlow
fp8 · cached $0.028
$0.22 / $0.66+317% vs list
GMICloud
fp8 · cached $0.0091
$0.286 / $0.858+442% vs list
NextBit
fp8 · cached $0.012
$0.352 / $1.06+567% vs list
Qwen (Alibaba)
Default region · cached $0.035
$0.352 / $1.06+567% vs list
Novita AI
fp8 · cached $0.026
$0.409 / $1.23+675% vs list
AtlasCloud
fp4 · cached $0.028
$0.44 / $1.32+733% vs list
Baidu
fp8 · cached $0.014
$0.44 / $1.32+733% vs list
Cloudflare Workers AI
Default region · cached $0.014
$0.44 / $1.32+733% vs list
Phala
Default region · cached $0.028
$0.44 / $1.32+733% vs list

DeepSeek V4.1 Flash

Way to buyIn / out per 1M
Relace
Default region, cheapest · cached $0.005
$0.05 / $0.25-62% vs list
Morph
Default region · cached $0.0014
$0.072 / $0.288-52% vs list
OpenInference
fp4 · cached $0.01
$0.1 / $0.5-24% vs list
DeepInfra
fp8 · cached $0.0042
$0.14 / $0.42-20% vs list
DeepSeek API
The lab's own API · cached $0.003
$0.15 / $0.6List price
Sail Research
fp4 · cached $0.01
$0.13 / $0.75+9% vs list
Wafer
Default region · cached $0.006
$0.2 / $0.6+14% vs list
CoreWeave
fp8 · cached $0.03
$0.2 / $0.65+19% vs list
DekaLLM
Default region · cached $0.01
$0.1 / $1+24% vs list
Fireworks AI
Default region · cached $0.007
$0.22 / $0.66+26% vs list
StreamLake
fp8 · cached $0.004
$0.199 / $0.794+32% vs list
GMICloud
fp8 · cached $0.0045
$0.225 / $0.9+50% vs list
Krea
fp8 · cached $0.006
$0.225 / $0.9+50% vs list
Phala
Default region · cached $0.0055
$0.276 / $1.1+84% vs list
Novita AI
fp8 · cached $0.0057
$0.285 / $1.14+90% vs list
AtlasCloud
fp8 · cached $0.03
$0.3 / $1.2+100% vs list
Baseten
fp8 · cached $0.03
$0.3 / $1.2+100% vs list
DigitalOcean
Default region · cached $0.006
$0.3 / $1.2+100% vs list
Makora
fp8 · cached $0.006
$0.3 / $1.2+100% vs list
Modal
Default region · cached $0.03
$0.3 / $1.2+100% vs list
Parasail
fp8 · cached $0.006
$0.3 / $1.2+100% vs list
Qwen (Alibaba)
Default region · cached $0.03
$0.3 / $1.2+100% vs list
SiliconFlow
fp8 · cached $0.006
$0.3 / $1.2+100% vs list
Together AI
Default region · cached $0.006
$0.3 / $1.2+100% vs list
Venice
fp8 · cached $0.0075
$0.375 / $1.5+150% vs list

List prices from providers' pages on the date shown; your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Weekly: LLM API list prices that changed, Thursday mornings.