Jev glossary
API & ModelsMultilingual support
Language support
English is Jev's primary training language; other languages are accepted but less accurate, so test before relying on them.
- Category
- API & Models
- Also known as
- Multilingual support
- Reading time
- 1 min
- Related terms
- 3
- Directory entries
- 28
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
The models page is explicit: English is where accuracy is currently best, and other languages, including CJK scripts, are handled but not equally well. Non-English workloads need testing on your own content.
Confidence is the recommended guardrail in the meantime: watch it closely when routing non-English requests, and keep a human path for the cases that matter.
Tagsmodelslimits
Related terms
Definitions that connect to this one.
Text-only inputJev evaluates strings, JSON objects, and arrays of text; images, audio, and video are not supported and must be pre-processed.Core ConceptsConfidence gateA threshold on confidence that decides whether code acts, confirms first, or escalates to a person or a bigger model.Answers & Confidencejev-1.13.0The current versioned Jev build: $42 per billion input tokens, a 64k context, and 250,000 tokens per second.API & Models
From the Jev directory
Directory entries that go deeper on this term.
The model card for jev-1.13.0: $42 per billion input tokens with free output, a 64k context, 250k tokens per second, and how to list the models your account can call.
Jev Guides & ArticlesDocs#official#docs#models
Official
Standard Thinking's merged BF16 3B checkpoint of Standard One: it scores choice, noul and score questions and returns probabilities through POST /v1/systemone with no generated text. The v2.2 card reports 100.00% JevBench public easy and 79.97% on many-option questions.
Jev Models & Reimplementations#community#open-models#multilingual
Community
Standard Thinking's merged BF16 8B checkpoint of Standard One, in the repository that also carries the shared server code: bounded choice, noul and score questions get probabilities through POST /v1/systemone, with no generated answer text.
Jev Models & Reimplementations#community#open-models#multilingual
Community
The v2.2 PEFT LoRA adapter for Standard Thinking's Standard One 3B decision model, shipped with a merge recipe for Ministral-3-3B-Instruct; serving requires the merged checkpoint and the shared server code in the StandardOne-8B repository.
Jev Models & Reimplementations#community#open-models#local
Community
Standard Thinking's 8B LoRA adapter for the Standard One decision model: merge it with the supplied recipe and serve it, and it scores choice, noul and score labels over a scenario with calibrated probabilities via POST /v1/systemone, never generating text.
Jev Models & Reimplementations#community#open-models#local
Community
Fastino's 287M multilingual classification model in the GLiNER2.5 family: pass any label set at call time and get labels back in a single forward pass, with no prompt template and no generated tokens. It averages 56.7% exact-match on the Fast Decisions suite.
Jev Models & Reimplementations#community#open-models#local
Community
22 more matching entries in the full directory.
From the Jev AI model community
Posts from builders shipping with Jev right now.