What jevmodel.ai is
jevmodel.ai publishes independent reports on Jev, TypeSafe’s decision model, and on nearby decision-model workflows. The official product, documentation, and console are at typesafe.ai. This site does not sell API access and is not TypeSafe AI.
Compiled by jevmodel.ai. Independent educational site. Official Jev product, docs, and console: typesafe.ai. Other hostnames that reuse the jevmodel name are not this project.
- This site
- Independent reports on Jev and nearby decision-model workflows.
- Not
- TypeSafe AI, the Jev API, or another hostname that reuses the jevmodel name.
- Official product
- typesafe.ai · docs.typesafe.ai · console.typesafe.ai
This site
TypeSafe describes Jev as a System One model: unstructured state in, typed probabilistic decisions out. The three question types are Choice, Score, and Noul. jevmodel.ai records public write-ups of those calls next to language models, encoder classifiers, and other decision models.
The pairing reports, author-reported benchmark tables, workflow page, Jev Day 2026 notes, and Jevtember launch record all stay on this hostname. Measurements stay with their authors. We have not rerun those experiments.
Sources:[1] TypeSafe AI[25] Diogo Almeida (TypeSafe AI)[34] TypeSafe AI
TypeSafe AI and this site
TypeSafe AI builds Jev. The 15 September 2026 launch post lists input tokens at $0.042 per million, with output free. The models page, accessed 26 October 2026, lists jev-1.14.0 as the target of both jev-latest and jev-preview, and keeps jev-1.13.0 as a versioned id, at that same rate.
This project is independent of TypeSafe AI. We link the official docs, blog, and console so readers can open the product. We do not speak for TypeSafe, and TypeSafe does not edit these pages. Other hostnames that reuse the jevmodel name are not this site.
Sources:[25] Diogo Almeida (TypeSafe AI)[34] TypeSafe AI[26] TypeSafe AI
Official TypeSafe links
Product and launch posts are at typesafe.ai. API behavior is on docs.typesafe.ai. On 20 September 2026 TypeSafe posted that Jev is available with no waitlist and pointed new users to console.typesafe.ai. A follow-up said every account starts with $5 in credit, described as about 120 million tokens.
A list-price calculator on this site multiplies the published $0.042 rate by the token counts you enter. That page uses the models-page rate. It is not an invoice or a TypeSafe tool.
Sources:[25] Diogo Almeida (TypeSafe AI)[26] TypeSafe AI[27] TypeSafe AI[34] TypeSafe AI
Questions about jevmodel.ai
What is jevmodel.ai?
jevmodel.ai is an independent reports site on Jev, TypeSafe’s decision model, and on nearby decision-model workflows. It is not TypeSafe AI. The official product, documentation, and console are at typesafe.ai.
Is jevmodel.ai affiliated with TypeSafe AI?
No. TypeSafe AI builds Jev and publishes the docs and console. This site reads public posts and documentation, then records the workflows and the limits of the reported results. TypeSafe does not edit these pages.
Where is the official Jev API?
TypeSafe’s documentation is at docs.typesafe.ai. On 20 September 2026 TypeSafe posted that Jev is available with no waitlist and pointed new users to console.typesafe.ai. This site does not issue keys.
Sources:[26] TypeSafe AI[34] TypeSafe AI
Does this site rerun the benchmarks it publishes?
No. The benchmark tables keep author-reported workloads, sample sizes, and limits. We have not rerun those API calls. The pricing page uses TypeSafe’s published list rate of $0.042 per million input tokens, with output free.
Sources:[34] TypeSafe AI
Sources and reading notes
The summaries below are paraphrases. Each link opens the original source, including its surrounding context.
TypeSafe AI
Source checked:
[1] Jev and the Choice, Score and Noul primitives
The documentation describes Jev as a System One model that evaluates state and typed questions. Choice selects an option, Score evaluates a rubric, and Noul returns a probability for a statement.
API behavior documented by the provider. The page describes the three question types and includes no latency, accuracy, or cost comparison.
Diogo Almeida (TypeSafe AI) (@typesafeai)
Published:
Source checked:
[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.
TypeSafe AI
Source checked:
[34] Jev 1.14 and 1.13 model card: price, context and aliases
The models page lists jev-1.14.0 and jev-1.13.0 at $42 per billion / $0.042 per million input tokens, with output free. Default context is 64k tokens per request and 32k per question. The table lists Input as Text for both. Jev 1.14 is dated as available from 14 October 2026. Both jev-latest and jev-preview point at jev-1.14.0. A warning on the page says there is no preview build. jev-1.13.0 stays available as a versioned id.
Canonical model card as accessed 26 October 2026. On 15 October 2026 the same page pointed jev-latest at jev-1.13.0 and jev-preview at jev-1.14.0. Audio and video are excluded here; convert those to text or structured fields first. Image files and 262k context are documented under danger-zone headers on this page and on the Images page. Rate limits are per organization in the developer console.
TypeSafe AI (@typesafeai)
Published:
Source checked:
[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:
[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.