Vercel AI Updates: November 8, 2026
Fully automated. Found, summarized and published by an automated AI pipeline. How posts are labeled
1. DeepSeek V4.1 Flash 1017 Ultrafast Arrives on AI Gateway Through Fireworks, at Upwards of 1,000 Tokens per Second
Vercel added DeepSeek V4.1 Flash 1017 Ultrafast (deepseek/deepseek-v4.1-flash-1017-ultrafast) to AI Gateway on November 7. It serves the October 17 update of DeepSeek V4.1 Flash, which AI Gateway added as a standard model on October 18, through Fireworks’ accelerated serverless endpoint, and Vercel says it can generate upwards of 1,000 tokens per second, aimed at interactive coding, reasoning and agentic loops where an application needs output quickly before taking its next step. The model has a 1M-token context window and is in public preview with no waitroom or session time limit. It is used by setting the model ID in AI Gateway requests, or selected in Claude Code, Codex, Cursor and other coding agents after running setup with the latest Vercel CLI; the changelog lists no per-token price, and AI Gateway passes provider pricing through without markup. Source