Skip to content

Compare model prices

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

DeepSeek V3.2

A month of tokens

  • DeepSeek V3.2$27.07

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

Side by side

DeepSeek V3.2
Input per 1M$0.209
Output per 1M$0.31
Cached input$0.022
Batch in / outn/a
Blended (3:1)$0.234
Context164K
Routes14
ReleasedDec 1, 2025
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 V3.2

Way to buyIn / out per 1M
GMICloud
fp8 · cached $0.022
$0.209 / $0.31Same as list
AtlasCloud
fp8 · cached $0.13
$0.26 / $0.38+24% vs list
DeepInfra
fp4 · cached $0.13
$0.26 / $0.38+24% vs list
Venice
Default region · cached $0.13
$0.268 / $0.39+28% vs list
SiliconFlow
fp8 · cached $0.135
$0.259 / $0.42+28% vs list
Novita AI
fp8 · cached $0.135
$0.269 / $0.4+29% vs list
Baidu
fp8 · cached $0.028
$0.28 / $0.42+35% vs list
DigitalOcean
Default region · cached $0.09
$0.3 / $0.96+99% vs list
Qwen (Alibaba)
fp8 · cached $0.074
$0.371 / $1.11+137% vs list
Friendli
Default region · cached $0.25
$0.5 / $1.5+221% vs list
Google Vertex AI
Default region
$0.56 / $1.68+259% vs list
Phala
Default region · cached $0.5
$1 / $1+327% vs list
Mara
Default region
$3 / $4.5+1342% vs list
SambaNova
Default region
$3 / $4.5+1342% 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.