Skip to content

Compare model prices

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

Kimi K2.5

A month of tokens

  • Kimi K2.5$90.00

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

Side by side

Kimi K2.5
Input per 1M$0.45
Output per 1M$2.25
Cached input$0.07
Batch in / outn/a
Blended (3:1)$0.9
Context262K
Routes5
ReleasedJan 27, 2026
Leadersboard score1 (#55)

On the price map

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

Every route

Kimi K2.5

Way to buyIn / out per 1M
SiliconFlow
int4 · cached $0.07
$0.45 / $2.25Same as list
AtlasCloud
int4 · cached $0.2
$0.49 / $2.5+10% vs list
Novita AI
Default region · cached $0.095
$0.57 / $2.85+27% vs list
AWS Bedrock
us-east-2
$0.6 / $3+33% vs list
Venice
Default region · cached $0.209
$0.532 / $3.33+37% 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.