DeepSeek V4 Flash now runs updated weights on AI Gateway
Source
vercel.com
Author
Jerilyn Zheng
Date
Why it matters
If you're routing agentic coding workloads through DeepSeek on Vercel's AI Gateway, this tells you the underlying model just got substantially stronger on Terminal-Bench with zero code changes required on your end.
Key quotes
“DeepSeek V4 Flash now runs on updated weights by default on AI Gateway, with notably stronger agentic capabilities. On Terminal-Bench, it scores 82.7, up 25.8 points from 56.9 in the April preview.”
“Requests to deepseek/deepseek-v4-flash pick up the new weights automatically, with no change to the model ID or your code.”
“AI Gateway reflects provider pricing with no markup and does not charge a platform fee on inference, including on Bring Your Own Key (BYOK) requests.”
