Model
jev-1.13.0
jev-1.13.0 from TypeSafe AI, Fast class. List prices per million tokens, and what the public benchmarks say about it.
- Class
- Fast
- Input, per million
- $0.04
- Output, per million
- $0.00
- Cached input
- $0.00
- Context window
- 32,000
- Longest answer
- 4,096
- Processed in
- global
- Prices from
- 28 September 2026
Calling it
Jev answers typed questions, not free text. Name jev-1.13.0 in the model field and send response_format with a JSON schema whose fields are fixed choices, yes or no, or bounded scores; the answer comes back as JSON, with a calibrated probability for each field in zabio.decision. auto also uses it on its own for classification jobs whenever it is the cheaper answer for the request.
"model": "jev-1.13.0"Supports: JSON schema
auto can pick this model when it suits the job and the line you chose.
What it costs
- Input $0.04 and output $0.00 per million tokens, at the provider list price.
- Input read from cache: $0.00 per million tokens.
Public results for this model
No public benchmark results for this model yet, and Zabio has not tested it either.
How routing picks between these models
Model and company names are trademarks of their owners. Zabio uses these models through their vendors' APIs and is not affiliated with the vendors.