Qwen 3.8 Max 0902 now available on AI Gateway
Vercel's AI Gateway now offers Qwen 3.8 Max 0902, a new snapshot of Alibaba's Qwen 3.8 Max model, with improvements in coding on larger projects, long-horizon unsupervised work, agent runs, and vision…
Vercel's AI Gateway now offers Qwen 3.8 Max 0902, a new snapshot of Alibaba's Qwen 3.8 Max model, with improvements in coding on larger projects, long-horizon unsupervised work, agent runs, and vision…
Vercel has introduced per-user budgets on its AI Gateway, allowing teams to set dollar spending limits for each user, covering spend from all API keys and app tokens attributed to that user. Once a us…
Vercel's AI SDK harness layer now supports fx, its lightweight open-source coding agent, via the official @ai-sdk/harness-fx adapter, which connects over the Agent Client Protocol using @ai-sdk/harnes…
Vercel has released design.md, a single public file that lets coding agents build on-brand pages outside its codebases, after finding that a ported prompt produced inconsistent results across models. …
Vercel announced that users can now build and deploy eve agents directly from the Vercel dashboard, enabling them to create a deployed agent with a private Git repository and a new Vercel project in a…
Tencent's Hy4 Preview, an open-source Mixture-of-Experts model with 770B total parameters and 49B active per token, is now available on Vercel's AI Gateway, supporting a 1M-token context window for lo…
Vercel's AI SDK harness layer now supports Cursor through the official @ai-sdk/harness-cursor adapter, enabling applications to run Cursor as a coding agent via the same HarnessAgent interface. The ad…
Vercel has redesigned the filters on its Deployments page to help users find specific deployments faster, adding suggested filters, type-to-search, and natural language query support that automaticall…
Inclusion AI's Ling 3.0 Flash Fin, a finance-focused language model with a 256K token context window and up to 32K output tokens, is now available on Vercel's AI Gateway free through September 25. The…
Ora, a platform co-founded by Assaf Elovic and Liad Yosef, benchmarks every major AI agent on Vercel, running agents on live websites to measure agent-readiness, with an estimate that 99% of the web i…
Alibaba's Qwen 3.8 Flash model is now available on Vercel's AI Gateway, supporting text and image inputs with a 1 million token context window and up to 65k output tokens, recommended for coding, tool…
Vercel's Security Dashboard is now generally available on all plans, providing a unified view of security posture across accounts and projects, with automatic flagging of issues like team members with…
Vercel's AI Gateway now offers Google's Gemini 3.5 Transcribe model, which converts audio to text in two variants: a single-request mode and a live WebSocket mode that updates transcripts in real time…
Vercel's AI Gateway now offers GLM 5.3 Flash from Z.ai, a multimodal model supporting text and vision input with a 1M token context window. The model supports function calling, structured output, and …
Vercel's AI Gateway now offers Muse Image 1.0, the first image model from Meta Superintelligence Labs, which can generate and edit images from text prompts and reference images. The model, accessed vi…
Vercel's AI Gateway is offering MiniMax M3 and M2.7 models free through GMI Cloud until Sunday, September 6, using the -free model IDs (minimax/minimax-m3-free or minimax/minimax-m2.7-free). After the…
Vercel Connect is now generally available on all plans and in v0, allowing deployments to request short-lived, scoped tokens at runtime instead of storing long-lived provider secrets. The service incl…
Alibaba's Wan 3.0 video generation model is now available on Vercel's AI Gateway as `alibaba/wan-v3.0-video`, supporting text-to-video, image-to-video, first/last frame conditioning, and reference-bas…
Vercel's AI Gateway now supports asynchronous video generation, allowing applications to receive webhooks, poll for completion, or start a generation and retrieve results later, avoiding request timeo…
Ora, a platform that benchmarks AI agents on live websites, has tested every major agent including Claude Code, ChatGPT, Gemini, Hermes, OpenClaw, and Vercel's eve, and found that 99% of the web isn't…