Choose Auto, TokenLab Verified, or Official for each request, with prices shown up front. See what's new

Models

Compare models by price, context, and capability. The Official price is the model maker's published price.

DeepSeek

ModelContextMax outputOfficial priceVerified priceDiscount
deepseek-v4-proJSON modePrompt CacheReasoningTool useSupports prompt caching
Available
1M384KOfficial price
Input$0.66/1MOutput$1.98/1M
Verified price— Discount
—
—
deepseek-v4.1-flashJSON modePrompt CacheReasoningTool useVisionSupports prompt caching
Available
1M384KOfficial price
Input$0.15/1MOutput$0.60/1M
Verified price— Discount
—
—

All model series

1 series