Vercel has added DeepSeek V4.1 Flash 1017 Ultrafast through Fireworks. The public preview offers a one-million-token context window. Vercel claims output can exceed 1,000 tokens per second; this is a vendor figure, not our benchmark. The endpoint serves the October 17 model revision.
Vercel adds DeepSeek Ultrafast to AI Gateway
Sources
1
Get the app vidgetc
Tech, gaming & AI news — always at hand
Google Play · Soon App Store
Comments