Skip to content

Compare model prices

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

Gemma 4 31B

A month of tokens

  • Gemma 4 31B$15.80

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

Side by side

Gemma 4 31B
Input per 1M$0.09
Output per 1M$0.34
Cached input$0.05
Batch in / outn/a
Blended (3:1)$0.153
Context262K
Routes13
ReleasedApr 2, 2026
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

Gemma 4 31B

Way to buyIn / out per 1M
DeepInfra
turbo, fp4 · cached $0.05
$0.09 / $0.34Same as list
CoreWeave
fp4 · cached $0.1
$0.1 / $0.34+5% vs list
Venice
fp4 · cached $0.09
$0.12 / $0.36+18% vs list
Chutes
fp4 · cached $0.012
$0.12 / $0.37+20% vs list
DeepInfra
fp8
$0.13 / $0.38+26% vs list
Crusoe
bf16 · cached $0.14
$0.14 / $0.4+34% vs list
Friendli
Default region
$0.14 / $0.4+34% vs list
Novita AI
bf16
$0.14 / $0.4+34% vs list
Parasail
fp8 · cached $0.06
$0.15 / $0.4+39% vs list
DeepInfra
ultra, fp8
$0.27 / $0.76+157% vs list
SambaNova
Default region
$0.38 / $1.15+275% vs list
ModelRun
fp4 · cached $0.75
$0.75 / $1+433% vs list
SiliconFlow
fp8 · cached $0.25
$0.75 / $1+433% 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.