Venice AI (Reseller)
DeepSeek V4 Flash Pricing
API pricing for DeepSeek V4 Flash via Venice AI. Input tokens cost $0.138/1M, output tokens cost $0.275/1M with 1M context window.
Last updated:
ReasoningTools
Input Cost
$0.138
per 1M tokens
Output Cost
$0.275
per 1M tokens
Context Window
1M
tokens
Cost Calculator
Estimated Cost:
$0.00
Model Details
Reseller Venice AI
Model ID deepseek-v4-flash
Context Window 1M tokens
Max Output 32768 tokens
Cache Read Cost $0.028/1M
Sources