Head to head

GPT-4.1 nano vs DeepSeek V4 Flash (0731)

On a blended workload of one million input tokens and three million output tokens, DeepSeek V4 Flash (0731) is 1.3× cheaper than GPT-4.1 nano.

GPT-4.1 nanoDeepSeek V4 Flash (0731)
Provider OpenAI Together AI
Input / MTok $0.1 $0.14
Output / MTok $0.4 $0.28
Cache read / MTok $0.025
Context window 1,047,576 1,000,000
Blended 1M in + 3M out $1.30 $0.98
Status ga ga

GPT-4.1 nano detail   DeepSeek V4 Flash (0731) detail