For developers building on @vercel.
San Francisco & Global
Based in United States
- Tweets 1,208
- Following 5
- Followers 46,108
- Likes 130
GPT-6 Sol now leads DeepSecBench's Pareto frontier:
• Highest benchmark score
• 80% lower run cost than the runner-up (GPT-6 Astra)
vercel.com/ai-gateway/leader…
5
7
128
15,137
Microsoft Teams is now on Vercel Connect.
Your apps and agents run as a Teams bot. People mention it in channels or message it directly, and your code replies as the bot.
vc connect create microsoft-teams
10
2
128
23,048
GPT Image 2.5 supports image generation and editing on AI Gateway.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝙸𝚖𝚊𝚐𝚎({
𝚖𝚘𝚍𝚎𝚕: "𝚘𝚙𝚎𝚗𝚊𝚒/𝚐𝚙𝚝-𝚒𝚖𝚊𝚐𝚎-𝟸.𝟻-𝚜𝚞𝚗𝚋𝚞𝚛𝚜𝚝",
𝚙𝚛𝚘𝚖𝚙𝚝: "𝙰𝙸 𝙶𝚊𝚝𝚎𝚠𝚊𝚢 𝚟𝚒𝚗𝚝𝚊𝚐𝚎 𝚜𝚒𝚐𝚗",
});
Try now: imagen.sh
8
63
5,922
MiniMax H3 and H3 Max are 50% off on AI Gateway until Sept 13.
Try them in video.vercel.sh
8
2
56
13,008
OpenAI’s Astra now leads the DeepSecBench cybersecurity benchmark.
Astra's cost per task is slightly above the previous leader 5.6 Sol, while improving benchmark runtime by over 2 hours.
vercel.com/ai-gateway/leader…
9
5
95
16,899
MiniMax H3 and H3 Max from @MiniMax_AI are 50% off on AI Gateway through Sept 13.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚖𝚒𝚗𝚒𝚖𝚊𝚡/𝚖𝚒𝚗𝚒𝚖𝚊𝚡-𝚑𝟹-𝚖𝚊𝚡',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚙𝚊𝚛𝚛𝚘𝚝𝚜 𝚒𝚗 𝚜𝚏',
});
vercel.com/changelog/minimax…
7
9
247
109,082
Muse Image is live on AI Gateway.
𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝙸𝚖𝚊𝚐𝚎({
𝚖𝚘𝚍𝚎𝚕: '𝚖𝚎𝚝𝚊/𝚖𝚞𝚜𝚎-𝚒𝚖𝚊𝚐𝚎-𝟷.𝟶',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝟾 𝚋𝚒𝚝 𝚙𝚊𝚕𝚊𝚌𝚎 𝚘𝚏 𝚏𝚒𝚗𝚎 𝚊𝚛𝚝𝚜',
})
vercel.com/changelog/muse-im…
4
3
76
5,443
Vercel Agent now works in @slackhq Code, with your app's full production context and zero setup.
▪︎ Connect secrets, env vars, commands, repos
▪︎ Steer the agent as a team
▪︎ Review diffs and ship directly in code channels
vercel.com/changelog/vercel-…
4
7
81
15,530
Introducing fx, a tiny, open, native coding agent from Vercel Labs.
Originally an internal tool, fx is a harness and CLI written in Zig, optimized for research and embedding in larger systems. Today, we're open sourcing it.
fx is built on three principles:
1. Fast. A single native binary, no runtime to install. It cold starts in 10µs and does no unnecessary work or I/O before accepting input. fx is the answer to "how fast can a coding agent be?"
2. Light. The 6.3MiB binary uses single-digit megabytes of memory at baseline, made for instant installation and embedding in resource-constrained environments and agent sandboxes.
3. Open. Apache-2.0, model and provider agnostic, suitable for local and cloud inference. Its small core extends through skills, plugins, and MCP.
Minimalism is an obsession throughout the entire harness: system prompt, tools, features, binary. The goal was to keep context usage and time to first token low, and make fx optimal for model benchmarking, sandboxing, evals, and gyms.
You can use fx directly or embed it as infrastructure. The CLI feels more like a Unix shell than an IDE in the terminal: it preserves scroll history, produces minimal output, and uses complex TUI rendering very, very sparingly. Programmatically, 𝚏𝚡 𝚊𝚜𝚔 --𝚓𝚜𝚘𝚗 gives structured output, 𝚏𝚡 𝚊𝚌𝚙 connects to editors and other clients, and WebAssembly can even run the whole thing inside the browser (see: fx.sh/try).
Privacy is a design constraint: no product telemetry, sessions and usage stay local, and no source code or prompts are shared with any endpoint other than inference. With local inference and auto-updates off, fx is fully hermetic.
fx is experimental. Use at your own risk and expect frequent changes. Chat with us on X (fx.sh/xchat) or file issues (fx.sh/issues).
𝚌𝚞𝚛𝚕 -𝚏𝚜𝚂𝙻 𝚏𝚡.𝚜𝚑/𝚜𝚎𝚝𝚞𝚙.𝚜𝚑 | 𝚋𝚊𝚜𝚑
fx.sh/
184
271
2,826
962,006
GLM 5.3 is coming soon to AI Gateway.
The highest-scoring open model in DeepsecBench, at 1/3 of the cost of some proprietary models with similar scores.
22
17
283
197,531
Introducing Vercel Managed Images.
Vercel Sandbox now ships with:
▪︎ Ubuntu as the default OS
▪︎ Preinstalled coding agents (𝚌𝚘𝚍𝚎𝚡, 𝚌𝚕𝚊𝚞𝚍𝚎…)
▪︎ Customizable, open source base images
Try the new base image:
$ 𝚗𝚙𝚡 𝚜𝚊𝚗𝚍𝚋𝚘𝚡@𝚕𝚊𝚝𝚎𝚜𝚝 𝚜𝚑
16
23
347
76,161
Seedance 2.5 is now on AI Gateway.
𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚋𝚢𝚝𝚎𝚍𝚊𝚗𝚌𝚎/𝚜𝚎𝚎𝚍𝚊𝚗𝚌𝚎-𝟸.𝟻',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚍𝚛𝚎𝚊𝚖𝚌𝚘𝚛𝚎 𝚜𝚊𝚗 𝚏𝚛𝚊𝚗𝚌𝚒𝚜𝚌𝚘',
})
9
11
198
68,476
Install a Marketplace integration with one command, and your agents already know how to use it.
10
7
81
16,350
Qwen 3.8 Max is available on AI Gateway.
It scores mid-pack on the DeepsecBench cybersecurity leaderboard at one of the lowest costs per run.
𝚖𝚘𝚍𝚎𝚕: '𝚊𝚕𝚒𝚋𝚊𝚋𝚊/𝚚𝚠𝚎𝚗𝟹.𝟾-𝚖𝚊𝚡'
8
9
114
48,331
MiniMax H3 is now on AI Gateway.
Try it:
𝚌𝚘𝚗𝚜𝚝 { 𝚟𝚒𝚍𝚎𝚘𝚜 } = 𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚖𝚒𝚗𝚒𝚖𝚊𝚡/𝚖𝚒𝚗𝚒𝚖𝚊𝚡-𝚑𝟹',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝟾-𝚋𝚒𝚝, 𝚋𝚕𝚊𝚌𝚔 𝚊𝚗𝚍 𝚠𝚑𝚒𝚝𝚎 𝚊𝚗𝚒𝚖𝚊𝚝𝚒𝚘𝚗 𝚘𝚏 𝚜𝚊𝚗 𝚏𝚛𝚊𝚗𝚌𝚒𝚜𝚌𝚘',
});
9
16
209
81,440
Nano Banana 2 Lite is now on AI Gateway, 1/2 the cost of previous models.
𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚃𝚎𝚡𝚝({
𝚖𝚘𝚍𝚎𝚕: '𝚐𝚘𝚘𝚐𝚕𝚎/𝚐𝚎𝚖𝚒𝚗𝚒-𝟹.𝟷-𝚏𝚕𝚊𝚜𝚑-𝚕𝚒𝚝𝚎-𝚒𝚖𝚊𝚐𝚎',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚅𝚎𝚛𝚌𝚎𝚕 𝚌𝚘𝚗𝚝𝚊𝚒𝚗𝚎𝚛 𝚜𝚑𝚒𝚙 𝟾-𝚋𝚒𝚝',
});
5
4
200
9,337
Drop It. It's Live.
Drag a file or folder into your browser and Vercel Drop gives you a production URL in seconds.
vercel.com/changelog/vercel-…
45
69
998
471,966
Use the observability dashboard to track AI Gateway usage
▪︎ Graph cost and requests
▪︎ Group by model or project
Add tags to AI SDK calls and search with the Custom Reporting API
▪︎ Ask your agent questions about the data
▪︎ Build a custom dashboard in v0
10
8
75
8,319
Grok Imagine Video 1.5 on AI Gateway.
Image-to-video generation with synced audio in one pass.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚒𝚖𝚊𝚐𝚒𝚗𝚎-𝚟𝚒𝚍𝚎𝚘-𝟷.𝟻-𝚙𝚛𝚎𝚟𝚒𝚎𝚠',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚊 𝚛𝚊𝚋𝚋𝚒𝚝 𝚜𝚙𝚛𝚒𝚗𝚝𝚒𝚗𝚐 𝚝𝚑𝚛𝚘𝚞𝚐𝚑 𝚗𝚢𝚌'
});
183
108
889
5,404,904
You can now filter workflow logs to easily view all logs for a workflow run in one place.
Jump directly from a run to logs, filter by steps, and quickly find relevant requests.
5
5
88
15,412
Seedance 2.0 is now on AI Gateway.
Generate photorealistic, multi-shot videos. Try it:
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚋𝚢𝚝𝚎𝚍𝚊𝚗𝚌𝚎/𝚜𝚎𝚎𝚍𝚊𝚗𝚌𝚎-𝟸.𝟶',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝙱𝚕𝚊𝚌𝚔 𝚝𝚛𝚒𝚊𝚗𝚐𝚕𝚎 𝚣𝚒𝚙𝚜 𝚊𝚌𝚛𝚘𝚜𝚜 𝚘𝚏𝚏𝚒𝚌𝚎'
})
12
26
536
50,479
AI-powered dating app Known's founder @celesteamadon shares how Vercel unlocks iteration velocity.
Known deploys to preview environments continuously, enabling 2-3 App Store submissions a week.
7
3
68
14,937
Vercel CDN now has a dedicated dashboard experience.
• Generate rules with AI prompts
• Update routing rules without redeploying
• View a live map of your global traffic
• Purge cache by tag instantly
Start building on Vercel with just a domain.
3
4
139
10,863
Anyone can build a Slack agent on Vercel, even if you've never touched OAuth scopes or webhook verification.
You just need the right skill.
▲ ~/ 𝚗𝚙𝚡 𝚜𝚔𝚒𝚕𝚕𝚜 𝚊𝚍𝚍 𝚟𝚎𝚛𝚌𝚎𝚕-𝚕𝚊𝚋𝚜/𝚜𝚕𝚊𝚌𝚔-𝚊𝚐𝚎𝚗𝚝-𝚜𝚔𝚒𝚕𝚕
16
36
592
109,699
Proud to support @openclaw on Vercel.
Open source at scale needs friends. @vercel stepped up and sponsors openclaw.ai + clawhub.com.
Grateful. 🦞
51
105
1,847
159,333
AI agents can now autonomously discover and install Marketplace integrations using the Vercel CLI.
▲ ~/ 𝚗𝚙𝚡 𝚜𝚔𝚒𝚕𝚕𝚜 𝚊𝚍𝚍 𝚟𝚎𝚛𝚌𝚎𝚕/𝚟𝚎𝚛𝚌𝚎𝚕 --𝚜𝚔𝚒𝚕𝚕 𝚟𝚎𝚛𝚌𝚎𝚕-𝚌𝚕𝚒
Install the CLI skill and ask your coding agent to integrate a Vercel Marketplace product.
39
102
1,094
210,747
Nano Banana 2 is on AI Gateway, now with web search and configurable thinking levels.
𝚒𝚖𝚙𝚘𝚛𝚝 { 𝚜𝚝𝚛𝚎𝚊𝚖𝚃𝚎𝚡𝚝 } 𝚏𝚛𝚘𝚖 '𝚊𝚒';
𝚌𝚘𝚗𝚜𝚝 𝚛𝚎𝚜𝚞𝚕𝚝 = 𝚜𝚝𝚛𝚎𝚊𝚖𝚃𝚎𝚡𝚝({
𝚖𝚘𝚍𝚎𝚕: '𝚐𝚘𝚘𝚐𝚕𝚎/𝚐𝚎𝚖𝚒𝚗𝚒-𝟹.𝟷-𝚏𝚕𝚊𝚜𝚑-𝚒𝚖𝚊𝚐𝚎-𝚙𝚛𝚎𝚟𝚒𝚎𝚠',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝙶𝚎𝚗𝚎𝚛𝚊𝚝𝚎 𝚊𝚗 𝚒𝚖𝚊𝚐𝚎 𝚘𝚏 𝚝𝚑𝚎 𝟸0𝟸𝟼 𝚂𝚞𝚙𝚎𝚛 𝙱𝚘𝚠𝚕 𝚊𝚝 𝚐𝚘𝚕𝚍𝚎𝚗 𝚑𝚘𝚞𝚛',
});
15
3
95
18,383
Grok Imagine Video is now on AI Gateway.
Text-to-video. Image-to-video. Video editing. Audio.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚡𝚊𝚒/𝚐𝚛𝚘𝚔-𝚒𝚖𝚊𝚐𝚒𝚗𝚎-𝚟𝚒𝚍𝚎𝚘',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚋𝚒𝚛𝚍𝚜 𝚊𝚌𝚛𝚘𝚜𝚜 𝚜𝚞𝚗𝚜𝚎𝚝'
});
2
6
53
44,826
Kling video models are now on AI Gateway.
Text-to-video. Image-to-video. Multi-shot. First & last frame.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚔𝚕𝚒𝚗𝚐𝚊𝚒/𝚔𝚕𝚒𝚗𝚐-𝚟𝟹.𝟶-𝚝𝟸𝚟',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚋𝚎𝚊𝚌𝚑 𝚜𝚌𝚎𝚗𝚎𝚜'
});
5
5
54
8,879
Google Veo is now on AI Gateway.
Text-to-video. Image-to-video. Native audio. Dialog.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚐𝚘𝚘𝚐𝚕𝚎/𝚟𝚎𝚘-𝟹.𝟷-𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎-𝟶𝟶𝟷',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚜𝚎𝚛𝚎𝚗𝚎 𝚕𝚊𝚗𝚍𝚜𝚌𝚊𝚙𝚎𝚜 𝚊𝚗𝚍 𝚖𝚘𝚝𝚒𝚘𝚗'
});
3
4
65
3,468
Wan video models are now on AI Gateway, and free for a limited time.
Text-to-video. Image-to-video. Character reference.
𝚊𝚠𝚊𝚒𝚝 𝚐𝚎𝚗𝚎𝚛𝚊𝚝𝚎𝚅𝚒𝚍𝚎𝚘({
𝚖𝚘𝚍𝚎𝚕: '𝚊𝚕𝚒𝚋𝚊𝚋𝚊/𝚠𝚊𝚗-𝚟𝟸.𝟼-𝚝𝟸𝚟',
𝚙𝚛𝚘𝚖𝚙𝚝: '𝚌𝚕𝚘𝚜𝚎 𝚞𝚙 𝚘𝚏 𝚊 𝚋𝚎𝚎'
});
4
10
79
9,436
We redesigned the runtime logs search bar.
Queries like 𝚕𝚎𝚟𝚎𝚕:𝚎𝚛𝚛𝚘𝚛 or 𝚜𝚝𝚊𝚝𝚞𝚜:𝟻𝟶𝟶 now parse into visual pills, making complex queries easier to scan and edit.
See it in action ↓
6
1
89
8,215
AssistLoop and cubic agents join the Vercel Agents Marketplace.
Add customer support and code review agents to your Vercel app with unified billing and account management ↓
3
4
69
6,754
We're releasing 𝚟𝚎𝚛𝚌𝚎𝚕-𝚛𝚎𝚊𝚌𝚝-𝚗𝚊𝚝𝚒𝚟𝚎-𝚜𝚔𝚒𝚕𝚕𝚜, extracted from the lessons of building v0 for iOS and the upcoming Vercel app (teaser below).
▲ ~/ npx skills add vercel-labs/agent-skills
58
219
3,070
489,670
Today, from Jan 14, 08:34 UTC to Jan 14, 14:17 UTC, Anthropic experienced elevated error rates on Opus 4.5 and Sonnet 4.5 models.
Vercel AI Gateway seamlessly failed over these requests to alternative providers like @awscloud Bedrock, achieving 99.99% uptime for tokens requested via Claude Code and custom-built agents.
5
9
238
20,609
You can now chat directly with your Vercel Marketplace integrations.
Ask questions, query data, or take action in plain English. Powered by MCP under the hood.
Try it with Neon, Supabase, Dash0, Stripe, Prisma and Mux, and more coming soon → vercel.fyi/integrations
4
10
74
25,002
You can now manage bulk redirects via UI, API, or CLI on Vercel. No deployment or code change required.
See how you can fix broken links in seconds ↓
6
2
76
6,505
You can now give every tenant their own preview environment using dynamic prefixes, like 𝚊𝚌𝚖𝚎---𝚙𝚛𝚎𝚟𝚒𝚎𝚠.𝚖𝚢-𝚜𝚒𝚝𝚎-𝚋𝚞𝚒𝚕𝚍𝚎𝚛.𝚍𝚎𝚟.
This enables multi-tenant platforms to create unique preview URLs that route to the correct deployment.
vercel.com/changelog/preview…
3
3
115
38,911
Introducing Vercel Knowledge Base.
Guides, tutorials, and best practices for developers building on @vercel.
8
33
463
21,298
Submissions for the AI Gateway Hackathon: Model Battlefield have been extended through December 15.
Win up to $1000 in AI Gateway credits.
Build a game where AI models compete.
7
9
81
14,840
We built v0 for iOS to deliver the best experience for building on the go.
Read the engineering deep-dive, highlighting our lessons from React Native & Expo at production scale ↓
15
16
171
78,749
Vercel Domains now supports AI search.
Go beyond keywords, describe what you’re looking for.
Try it now at vercel.com/domains
19
15
245
94,029
The Vercel Sandbox CLI is now available.
▲ ~ / 𝚗𝚙𝚡 𝚜𝚊𝚗𝚍𝚋𝚘𝚡 𝚛𝚞𝚗
Create, run, and manage secure, ephemeral Sandbox environments right from your terminal.
13
22
326
127,788
Microfrontends on Vercel create a unified experience across independent projects, from development through to delivery to your users.
1
36
6,700
Microfrontends support is now in Public Beta and available to teams on all plans.
Split large apps into smaller, independently deployed ones with their own tech stacks.
Vercel handles shared routing and fast navigation for smooth user experiences across microfrontends.
11
17
354
111,009
Qwen3-Coder inference on AI Gateway now runs on @cerebras, joining existing support from @deepinfra and @parasail_io.
You can now access Qwen3-Coder through Vercel AI Gateway, with no provider accounts required.
Set the AI SDK v5 𝚖𝚘𝚍𝚎𝚕 to '𝚊𝚕𝚒𝚋𝚊𝚋𝚊/𝚚𝚠𝚎𝚗𝟹-𝚌𝚘𝚍𝚎𝚛' to start building.
vercel.com/changelog/qwen3-c…
7
18
208
29,456
You can now customize how you display Observability query data with line charts, volume charts, or tables.
These settings can be saved with your queries in shareable notebooks.
1
1
17
1,821
Here's an interactive demo to see transform rules in action.
transforms-demo.vercel.app/
7
1,430
Pro teams now have a revamped usage dashboard with improved filtering, detailed breakdowns, and export options.
Recently introduced for Enterprise, it's now available to all paid teams.
vercel.com/changelog/new-usa…
1
1
45
6,580