Skip to content

Compare model prices

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

DeepSeek V3.1

A month of tokens

  • DeepSeek V3.1$44.00

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

Side by side

DeepSeek V3.1
Input per 1M$0.25
Output per 1M$0.95
Cached input$0.13
Batch in / outn/a
Blended (3:1)$0.425
Context164K
Routes8
ReleasedAug 21, 2025
Leadersboard scoren/a

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 243 models, lower left is cheaper

Every route

DeepSeek V3.1

Way to buyIn / out per 1M
DeepInfra
fp4 · cached $0.13
$0.25 / $0.95Same as list
Novita AI
fp8 · cached $0.135
$0.27 / $1+6% vs list
SiliconFlow
fp8
$0.27 / $1+6% vs list
AtlasCloud
fp8 · cached $0.13
$0.3 / $0.95+9% vs list
CoreWeave
fp8 · cached $0.55
$0.55 / $1.65+94% vs list
SambaNova
fp8
$0.65 / $1.5+103% vs list
Google Vertex AI
us-west2
$0.6 / $1.7+106% vs list
Mara
Default region
$0.6 / $1.7+106% 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.