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 0423

A month of tokens

  • DeepSeek V4 Flash 0423$6.84

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

Side by side

DeepSeek V4 Flash 0423
Input per 1M$0.049
Output per 1M$0.098
Cached input$0.0098
Batch in / outn/a
Blended (3:1)$0.061
Context1M
Routes16
ReleasedApr 24, 2026
Leadersboard scoren/a

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper

Every route

DeepSeek V4 Flash 0423

Way to buyIn / out per 1M
Baidu
fp8 · cached $0.0098
$0.049 / $0.098Same as list
StreamLake
fp8 · cached $0.0098
$0.049 / $0.098Same as list
DeepInfra
fp8 · cached $0.018
$0.09 / $0.18+84% vs list
GMICloud
fp8 · cached $0.018
$0.091 / $0.182+86% vs list
Venice
Default region · cached $0.02
$0.097 / $0.193+97% vs list
DigitalOcean
Default region · cached $0.02
$0.098 / $0.196+101% vs list
Qwen (Alibaba)
fp8 · cached $0.027
$0.134 / $0.268+174% vs list
SiliconFlow
fp8 · cached $0.028
$0.13 / $0.28+174% vs list
AtlasCloud
fp4 · cached $0.028
$0.14 / $0.28+187% vs list
Novita AI
fp8 · cached $0.028
$0.14 / $0.28+187% vs list
Parasail
fp8 · cached $0.07
$0.14 / $0.28+187% vs list
NextBit
fp8 · cached $0.035
$0.15 / $0.3+207% vs list
Mancer 2
fp8
$0.19 / $0.5+338% vs list
OpenInference
fp8 · cached $0.03
$0.14 / $0.7+358% vs list
Azure AI Foundry
us · cached $0.031
$0.21 / $0.56+387% vs list
Relace
fp4 · cached $0.016
$0.03 / $1.28+461% vs list

Sources: OpenRouter's public model catalog and each provider's own pricing page, read every morning at 05:00 UTC; gateway fees re-read every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.

Price changes by email

Thursdays, only in weeks when an LLM API list price changed.

Double opt-in. Unsubscribe any time.