Vercel

Google's Gemini 3.8 Flash now on AI Gateway with 1M token context window

Google's Gemini 3.8 Flash model is now available on AI Gateway with a 1 million token context window and support for text, image, PDF, and video inputs. It offers tool calling, web search, and outputs up to 65,536 tokens, with a 50% discount through December 31st.

Why it matters: The expanded context window and multimodal input capabilities enhance the model's utility for complex software engineering tasks. The integration with AI Gateway and discounted pricing could accelerate adoption among developers.

Qwen 3.8 Max 0902 AI model now available on Vercel AI Gateway

Alibaba's Qwen 3.8 Max 0902 is released on Vercel AI Gateway, improving coding on large projects, long-horizon tasks, and agent runs. It also enhances vision handling for charts and dense documents.

Why it matters: These improvements support more complex and autonomous coding workflows, potentially increasing developer productivity on large-scale projects. Enhanced vision capabilities aid in better interpreting visual data within documents.

Reader impact: Teams using AI at work may want to compare this against current productivity and review workflows.

Claude Fable 5.1 now available on AI Gateway

Claude Fable 5.1 from Anthropic is now available on AI Gateway. Fable 5.1 improvements compared to previous Claude models are concentrated in long, multi-stage work like agentic codi...

Vercel AI SDK Harness Layer Adds Support for fx Coding Agent

Vercel's AI SDK harness layer now supports fx, a lightweight open-source coding agent, enabling developers to run fx via a single API without separate integration. This update simplifies adding fx to applications using the HarnessAgent configuration.

Why it matters: Integrating fx through the AI SDK harness layer streamlines the use of coding agents in applications, reducing development overhead. This enhancement makes it easier for developers to leverage AI-powered coding assistance within their existing workflows.

Vercel AI Gateway adds per-user spending budgets

Vercel AI Gateway now allows setting dollar spending limits for each user on a team, covering all API keys and app tokens. Once the budget is reached, new requests are rejected until reset or increased.

Why it matters: This feature helps teams control and manage AI-related costs on a per-user basis, preventing unexpected overspending. It provides better budget oversight and spending discipline for AI API usage.

Reader impact: Teams using AI at work may want to compare this against current productivity and review workflows.

Vercel Sandbox shifts to daily snapshot storage cost calculation

Vercel now calculates charges for Sandbox snapshot storage based on each day's average usage instead of a monthly average. Users can monitor these daily charges on the team's Usage page.

Why it matters: This change allows for more precise billing aligned with actual daily usage, improving cost transparency and management for teams using Vercel Sandbox.

Vercel CLI adds commands for DNS, domains, and project management

Vercel CLI now includes dedicated commands to manage DNS records, domains, and projects directly from the terminal. Users can retrieve and update DNS configurations using record IDs, extending dashboard and API functionality to CLI workflows.

Why it matters: This update enables developers to handle domain and project configurations more efficiently through scripts or interactive terminal use, streamlining deployment and management tasks. It bridges the gap between GUI and CLI, enhancing automation and integration possibilities.

Reader impact: Developers may have a new tool, API, or workflow change worth testing against their own stack.