Jev is now available on the @vercel AI Gateway vercel.com/ai-gateway/mod…
CommunityPractices & Patterns
fx auto mode benchmarked with Jev
Vercel's Pranit reports benchmarking the fx auto-mode safety classifier with Jev: about 5 to 18 times faster and more accurate than GPT-5.6 Luna.
- Category
- Practices & Patterns
- Format
- Post
- Published by
- Community
- Author
- Pranit
- Added
- 2026-09-25
- Last verified
- 2026-09-25
Highlights
- Reports 5 to 18 times faster and more accurate than GPT-5.6 Luna, the previous top choice.
- Targets fx auto mode, the safety classifier that screens tool calls.
- A screenshot post with no published harness or dataset.
Watch out
A vendor engineer's summary; the raw numbers and evaluation code are not in the post.
Reactions & coverage
Posts, threads, and videos about this entry from around the web.
X: Jev lands on the Vercel AI Gateway
X: Vercel ships the AI SDK provider for Jev
Jev from @typesafeai is on AI Gateway. Build agents that decide, route, score, and stop in milliseconds: 𝚊𝚠𝚊𝚒𝚝 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎({ 𝚖𝚘𝚍𝚎𝚕: '𝚝𝚢𝚙𝚎𝚜𝚊𝚏𝚎-𝚊𝚒/𝚓𝚎𝚟', 𝚜𝚝𝚊𝚝𝚎, 𝚚𝚞𝚎𝚜𝚝𝚒𝚘𝚗𝚜, }); vercel.com/changelog/type…
X: Agent Handoff Gate: agents verify what they hand off
I built Agent Handoff Gate with typesafe Jev An experimental protocol for AI agents to verify worker evidence before handing results back to the lead. Less blind trust, fewer useless review loops. github.com/zsoXi/agent-ha…
X: Jev as an LLM guardrail inside Agentgateway
TypeSafe’s new Jev model is fast 🔥 and Agentgateway keeps up! In minutes, I had Jev running as a prompt guard through Agentgateway, with distributed tracing and cost tracking. Check out the example below Example: github.com/agentgateway/a… Intro to Jev: typesafe.ai/blog/introduci…
More like this
Vercel CTO Malte Ubl reports that Jev beat an existing classifier eval previously run on Gemini 2.5 Flash Lite, saturating the eval on quality and running 6x faster.
Practices & PatternsPost#community#x#evaluation
Community
An internal benchmark report: Jev zero-shot came within about 5 points of recall of a fine-tuned model at matched precision, at roughly $70 a month.
Practices & PatternsPost#community#x#benchmark
Community
The WebMCP benchmark author reports that Jev paired with the small Mercury 2.5 model solved 100% of tasks at roughly 112x lower model cost than GPT-6 Astra with computer use.
Practices & PatternsPost#community#x#benchmark
Community
From the community
Posts from builders shipping with Jev right now.
How the agent stack moved in Jev's first three days
Jev just landed and the agent stack moved in three days. TypeSafe AI released Jev on September 15. It is built for the work agents actually do most of the time: choose the next tool, score a risk, decide whether to retry, or answer yes or no. Latency is under half a second. Show more
Jev plays Doom at ~10 calls/sec for ~$7/hour
We love how this doomo doomonstrates real-time intelligence and what can be doone with code + AI! ~10 calls/sec = ~$7/hour
Jev plays Super Mario Bros.
got @typesafeai’s new model Jev to play Super Mario Bros. fast inference + structured outputs makes it surprisingly good for real time use cases. I'm excited to see what can be done with these new models!
LLMs generate answers, Jev makes decisions
this is the easiest way to understand Jev: LLMs generate answers. Jev makes decisions. that sounds like a small difference, but it actually changes the entire use case. say you give a normal LLM this: “here’s a user, their account history, payment behavior, support chats, Show more
@CompleteSkeptic
After co-inventing ChatGPT, I kept asking myself: why have superhuman chat models not led to AGI? I’ve spent the last 2 years in stealth building a new way to train models (RLCD), and a new type of frontier AI model that we are releasing today: Jev • 20-200x faster • 40-400x
Arbitrary classification as a primitive
Jev is cool not because it re-invented classification, but because it makes ARBITRARY classification into a type-safe programmable primitive. A general purpose zero shot decision model whose native interface is RUNTIME-DEFINED typed decisions, optimized for that exact interface
If you called Yann LeCun an idiot for saying we need to move beyond LLMs and build something new, you are banned from using Jev.
How Jev makes agents faster and cheaper
Jev solved local harness/model routing I use a combination of Claude Code, Codex and Opencode as my local agentic stack and routing to other harnesses was always enforced in the system prompt/rules With a deterministic hook that Claude Code can decide before delegation, Jev Show more