Sam Chitgopekar retweeted
Meet Glyph Cluster on AI Gateway.
πππππππ/πππ’ππ-πππππππ
β’ Free while in stealth for a limited time
β’ Access restricted to paid users
β’ Use it for coding & agentic knowledge work
β’ Prompts may be used for model improvement
vercel.com/changelog/glyph-cβ¦
Sam Chitgopekar retweeted
Vercel is the best security team we have worked with. The entire management chain is hyper paranoid and wonderful to work with! We will release more on these container escapes once the patches land! Stay tuned!
Sam Chitgopekar retweeted
Meet Pixel Canary on Vercel AI Gateway.
β’ πππππππ/πππ‘ππ-ππππππ’
β’ Free in stealth for a limited time
β’ Agentic coding & mobile app dev
β’ Ties GPT-6 Astra on Next.js evals
β’ Prompts may be used for model improvement vercel.com/changelog/pixel-cβ¦
Sam Chitgopekar retweeted
happening next week!!
Sam Chitgopekar retweeted
Grok 4.7 is live on AI Gateway, fx, and @eve.
40% off on all until September 27th.
ππππππ‘ππ/ππππ-πΊ.π½
vercel.com/changelog/grok-4-β¦
Sam Chitgopekar retweeted
Jev by @typesafeai is free on Vercel AI Gateway until Sept 25.
Build with the fastest adopted model on the Gateway at no cost.
vercel.com/ai-gateway/modelsβ¦
xitter.cf/vercel/status/21010773β¦
Jev was adopted faster than any other model in AI Gateway history.
In the first day, @typesafeai reached ~13% of teams, 2x the GPT-5.6 family and 6x Fable 5.1.
Sam Chitgopekar retweeted
New model index found that only @vercel has Jev.
Check it out yβall: computesdk.com/benchmarks/aiβ¦
Sam Chitgopekar retweeted
It's time to accelerate open weight models to the frontier.
And bring abundant tokens to all.
Today we launch Forge in partnership with Arcee, Microsoft, Vercel, Fireworks, and DigitalOcean:
Sam Chitgopekar retweeted
My @vercel internship: Codex, async video, batch support on AI Gateway. And I turned the terminal into an arcade for agents:
βͺοΈ Challenge models in 3D ASCII, no GPU
βͺοΈ Build with the open source game engine
Install β npm i -g ascii-arcade
Explore β ascii-arcade.dev
Sam Chitgopekar retweeted
GPT Image 2.5 supports image generation and editing on AI Gateway.
ππ πππ πππππππππΈππππ({
πππππ: "ππππππ/πππ-πππππ-πΈ.π»-ππππππππ",
ππππππ: "π°πΈ πΆππππ ππ’ πππππππ ππππ",
});
Try now: imagen.sh
Sam Chitgopekar retweeted
try on vercel ai gateway!
Muse Spark 1.3 is live on AI Gateway. Run it at standard rates, or 90% cheaper if you contribute training data back to Meta.
β’ ππππ/ππππ-πππππ-π·.πΉ
β’ ππππ/ππππ-πππππ-π·.πΉ-πππππππππππ
vercel.com/changelog/muse-spβ¦
Sam Chitgopekar retweeted
Set per-user budgets on AI Gateway.
β² ~/ ππ ππ-πππππ ππ’ πππππππ ππππππππ \
πππ ππππ --πππππ π»πΆπΆ \
--πππππππ-ππππππ πππππππ’
This works with existing team, project, and API key budgets.
vercel.com/changelog/set-perβ¦
Sam Chitgopekar retweeted
There are no teams in the industry as locked in + talent dense as Vercel AI Gateway.
Join them: vercel.com/careers/software-β¦
Sam Chitgopekar retweeted
We're introducing Run SDK: secure ππππ for dynamic Code Mode execution.
When agents write code, you don't always need a full sandbox. You can πππ their code in a lightweight QuickJS secure context. Faster and more cost-efficient.
πππ π πππ
vercel.com/blog/introducing-β¦
Sam Chitgopekar retweeted
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 10Β΅s 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, ππ‘ πππ --ππππ gives structured output, ππ‘ πππ 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).
ππππ -ππππ» ππ‘.ππ/πππππ.ππ | ππππ
fx.sh/
Sam Chitgopekar retweeted
Try now on vercel.com/ai-gateway/modelsβ¦
278.3 tok/s. $0.13/1M input. $0.27/1M output. full BF16
DeepSeek V4 Flash is now live on RunInfra -- the fastest full-precision V4 Flash inference anywhere, at the cheapest price
runinfra.ai/inference-api/qwβ¦
Sam Chitgopekar retweeted
Drill into every AI Gateway request.
βͺοΈ Inspect cost, token breakdown, duration, model, provider, and region
βͺοΈ Trace the full fallback path across provider attempts, failures first
vercel.com/changelog/ai-gateβ¦
