Last updated 16 Nov 2026. Sources last checked 16 Nov 2026.
Jev
TypeSafe AI · Released 15 Sep 2026
TypeSafe's first System One model: a frontier model built to return typed, calibrated decisions that software can use directly, rather than generated text. Official uses include structured judgments with probabilities and confidence scores defined in advance.
- Maker
- TypeSafe AI
- Release date
- 15 Sep 2026
- First seen
- 15 Sep 2026
- Access
- Early access via TypeSafe; waitlist at typesafe.ai, as stated in the launch announcement.
- Pricing (as publicly stated)
- As stated on 15 Sep 2026: $0.042 per million input tokens; output tokens free.
- Modalities
- text
- Question types
- typed structured values with calibrated probabilities
- Latency (as stated)
- TypeSafe stated end-to-end response time of 70ms-500ms in the launch post.
- Official announcement
- https://typesafe.ai/blog/introducing-system-one-models-and-jev
Benchmark claims
These are claims as published by the maker or in the linked official post. This catalog has not independently rerun every benchmark.
TypeSafe said Jev achieves similar levels of intelligence on System One tasks compared with existing LLMs, while being two orders of magnitude faster and more efficient, and that it cannot hallucinate because it does not generate strings.
What enterprises should know
Cost and pricing
As stated on 15 Sep 2026: $0.042 per million input tokens; output tokens free. Figures are what the maker stated in the linked source and may have changed.
Lock-in
The official announcement describes access as follows: Early access via TypeSafe; waitlist at typesafe.ai, as stated in the launch announcement. The announcement did not state a documented export path or switching process beyond that description.
Security and privacy
The official announcement we sourced did not state a specific security certification or independent privacy audit for this product. If you use a hosted endpoint named in the announcement, inputs are sent to that host under the host's own terms.
Maturity and availability
The maker's official announcement is dated 2026-09-15. Access was described as: Early access via TypeSafe; waitlist at typesafe.ai, as stated in the launch announcement. TypeSafe stated end-to-end response time of 70ms-500ms in the launch post.
Compliance notes
The official announcement we sourced did not state a specific regulatory approval or compliance certification for this product.
What consumers should know
Cost and pricing
The announcement describes early or waitlist access rather than a consumer retail product. As stated on 15 Sep 2026: $0.042 per million input tokens; output tokens free.
Lock-in
Access was described as: Early access via TypeSafe; waitlist at typesafe.ai, as stated in the launch announcement. Joining a waitlist or hosted service may require an account with the maker.
Security and privacy
Using a hosted endpoint means prompts and other inputs are sent to the maker or host named in the announcement. The announcement we sourced did not state a privacy policy unique to this product beyond that company's existing terms.
Maturity and availability
The official announcement is dated 2026-09-15. Availability was described as: Early access via TypeSafe; waitlist at typesafe.ai, as stated in the launch announcement. TypeSafe stated end-to-end response time of 70ms-500ms in the launch post. This summary does not say whether the product is suitable for a particular consumer task.
Compliance notes
The official announcement we sourced did not state consumer-protection certifications specific to this product.
Figures are as stated in the linked source on the date shown. Sources last checked 16 Nov 2026. Names and marks belong to their owners. This page is an independent summary, not a product page from TypeSafe AI.