Skip to content

Compare model prices

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

DeepSeek V4 Pro 0423

A month of tokens

  • DeepSeek V4 Pro 0423$112.15

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

Side by side

DeepSeek V4 Pro 0423
Input per 1M$0.801
Output per 1M$1.6
Cached input$0.067
Batch in / outn/a
Blended (3:1)$1
Context1M
Routes15
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 Pro 0423

Way to buyIn / out per 1M
StreamLake
fp8 · cached $0.067
$0.801 / $1.6Same as list
Baidu
fp8 · cached $0.067
$0.803 / $1.61Same as list
GMICloud
fp8 · cached $0.08
$0.957 / $1.91+19% vs list
DigitalOcean
Default region · cached $0.209
$1.04 / $2.09+30% vs list
Cloudflare Workers AI
Default region · cached $0.2
$1.15 / $2.55+50% vs list
DeepInfra
fp8 · cached $0.1
$1.3 / $2.6+62% vs list
Qwen (Alibaba)
fp8 · cached $0.118
$1.42 / $2.83+77% vs list
SiliconFlow
fp8 · cached $0.135
$1.5 / $3.14+91% vs list
Novita AI
fp8 · cached $0.135
$1.6 / $3.2+100% vs list
Venice
Default region · cached $0.33
$1.65 / $3.3+106% vs list
AtlasCloud
fp4 · cached $0.13
$1.68 / $3.38+110% vs list
Baseten
fp4 · cached $0.145
$1.74 / $3.48+117% vs list
NextBit
fp8 · cached $0.145
$1.74 / $3.48+117% vs list
Parasail
fp8 · cached $0.1
$1.74 / $3.48+117% vs list
Azure AI Foundry
us · cached $0.16
$1.91 / $3.83+139% 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.