Head to head

DeepSeek V4 Flash vs GPT-OSS 20B

On a blended workload of one million input tokens and three million output tokens, GPT-OSS 20B is 1.5× cheaper than DeepSeek V4 Flash.

DeepSeek V4 FlashGPT-OSS 20B
Provider DeepSeek Together AI
Input / MTok $0.14 $0.05
Output / MTok $0.28 $0.2
Cache read / MTok $0.0028
Context window 1,000,000 128,000
Blended 1M in + 3M out $0.98 $0.65
Status ga ga

DeepSeek V4 Flash detail   GPT-OSS 20B detail