VercelVercel added two models to AI Gateway and expanded Token Pass with a third. The releases cover long-context coding, faster text generation and subscription-based model access. They follow Vercel’s earlier AI Gateway releases in mid-October.
MiniMax M3.1 Flash Joins AI Gateway
MiniMax M3.1 Flash is available through AI Gateway for free until 22 October. The open-weight multimodal model has a 1M-token context window, with improved performance on complex agentic tasks, coding and cybersecurity. Developers can call minimax/minimax-m3.1-flash through the AI SDK, Chat Completions, Responses or Anthropic Messages APIs, while pinned requests will move to MiniMax’s standard rate after the free period.
Mercury 3 Arrives With Launch Pricing
Mercury 3 is now available on AI Gateway with 50% off launch pricing. Inception’s diffusion-based text generation model can generate more than 1,000 tokens per second and has a 1M-token context window, targeting latency-sensitive work such as browser agents and real-time search. Developers can use inception/mercury-3 through the AI SDK or configure it for coding agents with the Vercel CLI.
DeepSeek V4.1 Flash Enters Token Pass
DeepSeek V4.1 Flash is now included in Token Pass, using the latest 1017 weights. The $30-a-month subscription for Pro teams provides $80 in monthly AI credit and also includes Kimi K3 and GLM 5.3, with each model accessed through its preferred provider. It runs through AI Gateway with Zero Data Retention enabled by default and works with coding agents or custom AI SDK apps, building on the original Token Pass launch.
Sources
3 checkedHow we cover tool news: Create With's tool desk drafts these reports with AI from the sources listed above and checks them against those sources before publishing.
n8n
Netlify
Supabase
Kajabi