Skip to content

Compare model prices

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

Claude Opus 4.8

A month of tokens

  • Claude Opus 4.8$1,000

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

Side by side

Claude Opus 4.8
Input per 1M$5
Output per 1M$25
Cached input$0.5
Batch in / out$2.5 / $12.5
Blended (3:1)$10
Context1M
Routes11
ReleasedMay 27, 2026
Leadersboard score3 (#33)

On the price map

Size: context window, 8K to 2MEqual blended cost (3:1) 245 models, lower left is cheaper

Every route

Claude Opus 4.8

Way to buyIn / out per 1M
Anthropic API
The lab's own API · cached $0.5
$5 / $25List price
AWS Bedrock
Default region · cached $0.5
$5 / $25Same as list
Azure AI Foundry
global · cached $0.5
$5 / $25Same as list
Claude Platform on AWS
Default region · cached $0.5
$5 / $25Same as list
Google Vertex AI
global · cached $0.5
$5 / $25Same as list
AWS Bedrock
eu-west-1 · cached $0.55
$5.5 / $27.5+10% vs list
AWS Bedrock
us · cached $0.55
$5.5 / $27.5+10% vs list
Azure AI Foundry
us · cached $0.55
$5.5 / $27.5+10% vs list
Google Vertex AI
europe · cached $0.55
$5.5 / $27.5+10% vs list
Google Vertex AI
us · cached $0.55
$5.5 / $27.5+10% vs list
Anthropic
fast · cached $1
$10 / $50+100% 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.