Independent Jev reports|Not affiliated with TypeSafe AI
jevmodel.ai
Last updated:

Jevtember: September 2026 on Vercel AI Gateway

On 18 October 2026 TypeSafe CEO Diogo Almeida posted the word Jevtember, quoting a Vercel thread that called Jev the fastest-adopted model in AI Gateway history and September’s most-requested model. The nickname had already shown up on X on 19 September, four days after TypeSafe launched Jev.

Compiled by jevmodel.ai. Independent notes on the September 2026 launch weeks. Gateway percentages stay with Vercel. We have not rerun them.

■
Vercel AI Gateway, September 2026
JEVTEMBER
15 to 17 September
TypeSafe launch post on the 15th. Vercel changelog on the 16th. October index lists the gateway launch date as 17 September. Model id typesafe-ai/jev.
First 24 hours
Nearly 13% of paid teams. Twice the GPT-5.6 family. More than six times Fable 5.1. A tenth of teams within 18 hours.
First two weeks
35.3% reach among paid teams. Most requests of any September model. 55.6% of week-one teams returned in week two. 0.27% of gateway spend in that window.
Full September
1% of tokens, 0.15% of spend. Scorecard spend share 0.3%, composite 65.9, sixth among September launches.

Where the name came from

TypeSafe published Jev on 15 September 2026. The launch post presents it as a System One model: unstructured state in, typed probabilistic decisions out, at $0.042 per million input tokens with output free.

On 19 September Aaron Batilo posted a one-line Green Day parody, “Wake me up, when Jevtember ends.” Among the posts opened for this page, that is the earliest public use of the word. On 18 October Almeida quoted Vercel’s October AI Gateway Index thread and wrote only “Jevtember,” with the word also on the attached image.

Sources:[25] Diogo Almeida (TypeSafe AI)[174] Aaron Batilo[172] Diogo Almeida[173] Vercel

First days on AI Gateway

Vercel’s changelog listing Jev on AI Gateway is dated 16 September 2026. The model id is typesafe-ai/jev, reached through AI SDK 7’s experimental evaluate API from version 7.0.105. The October Production Index later prints the gateway launch date as 17 September.

On 18 September Vercel said that within 24 hours Jev reached more than twice as many paid teams as any previous model launch. By hour 24 nearly 13% of paid teams were using it, twice the GPT-5.6 family and more than six times Fable 5.1. A tenth of teams arrived within 18 hours. Every other recent launch stayed below 7% after a full day. A same-day Vercel post on X repeats the 13%, 2x, and 6x figures.

Vercel Developers also posted that Jev was free on AI Gateway until 25 September. That window sits inside the first two weeks the later index measures. The post does not say how much of the first-day share came from the promo.

Sources:[175] Rohan Taneja, Zachary Chen and Jerilyn Zheng (Vercel)[176] Amelia Charles, Harpreet Arora and Eric Dodds (Vercel)[28] Vercel[29] Vercel Developers[177] Amelia Charles and Harpreet Arora (Vercel)

The October index

Vercel’s October 2026 AI Gateway Production Index, published 15 October, ranks September model launches with at least two weeks of data. In its first two weeks Jev reached 35.3% of paid teams, nearly double Claude Sonnet 5.5 at 18.1%. The article calls that the fastest adoption of any model in AI Gateway history. Jev also received the most requests of any model in September, even though it launched halfway through the month. Of the teams that tried it in week one, 55.6% returned in week two, fifth among the launches in that table.

The opening summary says Jev accounted for 0.27% of gateway spend over those same first two weeks. Later in the article, Jev is 1% of September tokens and 0.15% of September spend. The full scorecard lists spend share as 0.3% and a composite score of 65.9, sixth among September launches. Vercel writes that a Jev request is faster and cheaper than a typical language-model call, and uses a fraction of the tokens.

Launch metrics cover external paid teams during each model’s first 14 days. Reach uses paid teams active from the start of the launch month through the data cutoff. Spend share uses total paid gateway spending during the model’s window. Return rate is the share of first-week teams that used the model again in week two. Spending is estimated at published list prices. The traffic is Vercel AI Gateway only.

Russell Brandom’s TechCrunch write-up rounds two-week reach to 35% and notes that the gateway undercounts labs that sell their own APIs. He also writes that Vercel replaced GPT-6 Luna with Jev for classifying harmful commands. That swap is TechCrunch’s account of Vercel’s own use.

Sources:[177] Amelia Charles and Harpreet Arora (Vercel)[173] Vercel[178] Russell Brandom

Access and a San Francisco Saturday

On 20 September TypeSafe posted that Jev was available with no waitlist and pointed new users to the console. A follow-up said every account starts with $5 in credit, described as about 120 million tokens.

Stephen Council of Business Insider attended a Jev hackathon on a Saturday at CodeRabbit’s San Francisco office. The article is dated 29 September 2026 and does not print that Saturday’s calendar date. Allie Laabs, TypeSafe’s head of developer relations, told the room Jev fits classification work such as sorting support queries. Council writes that TypeSafe’s Discord had more than 100,000 members and that the launch video had almost 40 million views on X. Named attendees describe faster tool selection and lower cost in their own products. The article prints no scored benchmark from the event.

Sources:[26] TypeSafe AI[27] TypeSafe AI[179] Stephen Council

After September

Jevtember is a name for the September 2026 launch weeks. Jev Day is TypeSafe’s 14 October 2026 release of Jev 1.14.0, with image input, a Box type, and 262k context behind danger-zone headers. The Jev Day hub on this site covers that cutover.

Sources:[153] TypeSafe AI[172] Diogo Almeida

Questions about Jevtember

What is Jevtember?

Jevtember is a nickname for the weeks after TypeSafe launched Jev on 15 September 2026. Aaron Batilo used it on X on 19 September. On 18 October TypeSafe CEO Diogo Almeida posted the word while quoting Vercel’s claim that Jev was AI Gateway’s fastest-adopted model and September’s most-requested model.

Sources:[25] Diogo Almeida (TypeSafe AI)[174] Aaron Batilo[172] Diogo Almeida[173] Vercel

When did Jev land on Vercel AI Gateway?

Vercel’s changelog is dated 16 September 2026. The October Production Index lists the gateway launch date as 17 September. The model id on the gateway is typesafe-ai/jev.

Sources:[175] Rohan Taneja, Zachary Chen and Jerilyn Zheng (Vercel)[177] Amelia Charles and Harpreet Arora (Vercel)

How large was first-day adoption on the gateway?

Vercel’s 18 September post said that by hour 24 nearly 13% of paid teams were using Jev, twice the GPT-5.6 family and more than six times Fable 5.1. A tenth of teams arrived within 18 hours.

Sources:[176] Amelia Charles, Harpreet Arora and Eric Dodds (Vercel)[28] Vercel

What did the October index add?

In Jev’s first two weeks Vercel recorded 35.3% reach among paid teams, the most requests of any September model, and a 55.6% week-two return rate. The same window accounted for 0.27% of gateway spend. For the full month Vercel puts Jev at 1% of tokens and 0.15% of spend.

Sources:[177] Amelia Charles and Harpreet Arora (Vercel)

Is Jevtember the same as Jev Day?

Jevtember refers to the September 2026 launch period. Jev Day is TypeSafe’s 14 October 2026 release of Jev 1.14.0, with images, Box, and 262k context behind danger-zone headers.

Sources:[172] Diogo Almeida[153] TypeSafe AI

Sources and reading notes

The summaries below are paraphrases. Each link opens the original source, including its surrounding context.

Diogo Almeida (TypeSafe AI) (@typesafeai)

Published:

Source checked:

Official

[25] Introducing System One models and Jev

The launch post describes Jev as a function-call style model: unstructured state in, typed probabilistic decisions out. It lists input tokens at $0.042 per million ($42 per billion), free output tokens, and a 70-500ms response time from request to answer.

Provider announcement covering System One models, RLCD, parallel sampling, and workflow-eval claims of 193.6× faster and 444.6× cheaper versus an LLM baseline. The figures come from TypeSafe’s evals. This site has not rerun them.

Aaron Batilo (@aaronbatilo)

Published:

Source checked:

X.com

[174] Wake me up when Jevtember ends

Aaron Batilo posted a one-line Green Day parody, “Wake me up, when Jevtember ends,” four days after TypeSafe launched Jev.

Dated 19 September 2026. The post has no adoption figures. It is an early public use of the nickname on X.

Diogo Almeida (@CompleteSkeptic)

Published:

Source checked:

X.com

[172] Almeida posts Jevtember quoting Vercel

Almeida posted the single word Jevtember, quoting Vercel’s 15 October thread that called Jev AI Gateway’s fastest-adopted model and September’s most-requested model. The attached image repeats the word.

Posted 18 October 2026. The post is a quote-tweet with no extra numbers. Replies include jokes and congratulations; they add no Gateway measurements.

Vercel (@vercel)

Published:

Source checked:

X.com

[173] Vercel names Jev fastest-adopted and most-requested

The second post in Vercel’s October 2026 AI Gateway Index thread said Jev became the gateway’s fastest-adopted model ever and September’s most-requested model.

Posted 15 October 2026 with a chart. The numeric tables live in the linked October Production Index, not in this post.

Rohan Taneja, Zachary Chen and Jerilyn Zheng (Vercel)

Published:

Source checked:

Web

[175] Jev listed on Vercel AI Gateway

Vercel listed Jev on AI Gateway as typesafe-ai/jev, reached through AI SDK 7’s experimental evaluate API from version 7.0.105. The changelog describes Choice, Score, and Boolean questions against shared state.

Changelog dated 16 September 2026. Boolean here is Vercel’s name for TypeSafe’s Noul primitive. The October index later prints the gateway launch date as 17 September.

Amelia Charles, Harpreet Arora and Eric Dodds (Vercel)

Published:

Source checked:

Web

[176] Jev is the fastest-adopted model in AI Gateway history

Vercel wrote that within 24 hours on AI Gateway, Jev reached more than twice as many paid teams as any previous model launch. By hour 24 nearly 13% of paid teams were using it, twice the GPT-5.6 family and more than six times Fable 5.1. A tenth of teams arrived within 18 hours. Every other recent launch stayed below 7% after a full day.

Blog dated 18 September 2026. The percentages are shares of paid AI Gateway teams. The post says the next test is whether first-day adoption lasts. It restates TypeSafe workflow evaluations as up to 194 times faster and 445 times cheaper; those figures originate with TypeSafe, not with a Vercel rerun.

Jev / GPT / ClaudeRead original

Vercel (@vercel)

Published:

Source checked:

X.com

[28] Jev adoption on Vercel AI Gateway

Vercel reported that Jev was adopted faster than any other model in AI Gateway history, reaching about 13% of teams on the first day, twice the GPT-5.6 family and six times Fable 5.1.

First-day Gateway adoption statistics from Vercel. The post describes Jev as typesafe-ai/jev through AI SDK 7 experimental_evaluate. The percentages are shares of Gateway usage.

Jev / GPT / ClaudeRead original

Vercel Developers (@vercel_dev)

Published:

Source checked:

X.com

[29] Promotional Jev pricing on Vercel AI Gateway

Vercel Developers announced that Jev was free on Vercel AI Gateway until 25 September.

Promotional Gateway pricing. Native TypeSafe list pricing remains $0.042 per million input tokens with free output, as documented on the model card.

Amelia Charles and Harpreet Arora (Vercel)

Published:

Source checked:

Web

[177] AI Gateway Production Index, October 2026

The October 2026 index names Jev the fastest-adopted model in gateway history. In its first two weeks Jev reached 35.3% of paid teams, received the most requests of any September model, and saw 55.6% of week-one teams return in week two. The opening summary puts that two-week window at 0.27% of gateway spend. Later in the same article, Jev accounts for 1% of September tokens and 0.15% of September spend. The scorecard lists spend share 0.3% and a composite score of 65.9, sixth among September launches. The table’s gateway launch date is 17 September.

Published 15 October 2026. Launch metrics cover external paid teams in each model’s first 14 days. Reach uses paid teams active from the start of the launch month through the data cutoff. Spend share uses total paid gateway spending during the model’s window. Return rate is first-week teams that used the model again in week two. Spending is estimated at list prices. The traffic is Vercel AI Gateway only.

Jev / Claude / GPTRead original

Russell Brandom

Published:

Source checked:

Web

[178] Jev is Vercel’s fastest-adopted AI model ever

Brandom reports Vercel’s October index: within two weeks Jev was used by 35% of paid teams, nearly double Sonnet 5.5. He notes the gateway undercounts labs that sell their own APIs. He also writes that Vercel replaced GPT-6 Luna with Jev for classifying harmful commands.

TechCrunch, 16 October 2026. The 35% figure rounds Vercel’s 35.3% two-week reach. The Luna replacement is TechCrunch’s account of Vercel’s own use; this page does not have a separate Vercel engineering post for that swap.

Jev / GPT / ClaudeRead original

TypeSafe AI (@typesafeai)

Published:

Source checked:

X.com

[26] Jev is available without a waitlist

TypeSafe announced that Jev is available to everyone, with no waitlist, and pointed new users to the console login.

Public-availability post five days after early access. A follow-up stated that every account starts with $5 in credit, described as about 120 million tokens.

TypeSafe AI (@typesafeai)

Published:

Source checked:

X.com

[27] Starter credit for new TypeSafe accounts

TypeSafe stated that all users start with $5 in credit, described as about 120 million tokens.

Posted alongside the no-waitlist announcement. At the listed $0.042 per million input tokens, that credit covers a large volume of Choice, Score and Noul calls. The token equivalent is the author’s figure.

Stephen Council

Published:

Source checked:

Web

[179] A Jev hackathon at CodeRabbit in San Francisco

Council attended a Jev hackathon on a Saturday at CodeRabbit’s San Francisco office. Allie Laabs, TypeSafe’s head of developer relations, told the room Jev fits classification work such as sorting support queries. Council writes that TypeSafe’s Discord had more than 100,000 members and that the launch video had almost 40 million views on X. Named attendees describe faster tool selection and lower cost in their own products; the article prints no scored benchmark from the event.

Business Insider, 29 September 2026. The Saturday is not given a calendar date. Qualitative comments stay with their speakers. A valuation rumor attributed to The Information is outside this page.

TypeSafe AI

Published:

Source checked:

Official

[153] Jev: For the builders AND dreamers

The Jev Day blog ships jev-1.14.0 under jev-preview, with experimental images, a Box type, and longer context behind danger-zone headers. TypeSafe says jev-latest will move to jev-1.14.0 in a week, jev-1.13.0 will stay available, and it intends 60 days of warning before deprecating 1.13.0 and 30 days for 1.14.0. Images are composable through an assets map. TypeSafe says models, including Jev, perform worse on multimodality than on pure text.

Company blog, metadata timestamp 15 October 2026 00:22 UTC; the models page dates Jev 1.14 as available from 14 October 2026. The Measuring Intelligence section describes an internal ranking of open-weight models and asks readers not to treat it as settled. The text we opened does not print those scores, so this site does not repeat a table we could not read as numbers.