Models & Pricing

Compare models

Choose two or three models. Copy the URL to share your selection.

ComparisonJev 1.13
jev-1.13
Choose model 2
TypeDecision—
Best forClassification, scoring and routing with probabilities—
TokenRex price$0.0295 per 1M tokens—
Cached input / 1M tokensNo separate cached rate listed—
Cache write / 1M tokensNot applicable—
Cached outputNot offered · standard output rate applies—
Web searchNot applicable—
Market price$0.0421 per 1M tokens—
Input token limit (provider)Within the context window—
Vendor input modalitiesState and typed questions—
Vendor output modalitiesProbabilistic decisions—
TokenRex endpointsPOST /v1/decisions—
Benchmarks
Benchmark evidence3 source-linked results—
Typed decisions — LocalLLaMA/typed-decisions frozen test split
0.74accuracy (0-1)

Independent third-party eval (not vendor-reported), frozen split, 2,000-sample bootstrap CI; zero-shot classification/scoring accuracy. Published Jev 1.13.0 checkpoint; the rolling latest API alias may change and is not independently pinned by TokenRex. Published source text: Independent benchmark ran Jev 1.13.0 on a frozen 400-case / 2,000-decision test split of LocalLLaMA/typed-decisions on 2026-09-20, reporting Accuracy 0.740 (95% CI 0.721–0.759).

DecisionEval — Jev by TypeSafe benchmark page
—
Typed decisions — calibration
0.148Brier score

Lower is better; independent third-party eval, frozen split dated 2026-09-20. Published Jev 1.13.0 checkpoint; the rolling latest API alias may change and is not independently pinned by TokenRex. Published source text: Same independent run reports Brier score (against gold probability distribution) of 0.148, 95% CI [0.139, 0.156].

DecisionEval — Jev by TypeSafe benchmark page
—
Belebele (122 languages)
86.7%

Zero-shot, jev-1.13.0, one frozen template per dataset, full evaluation split across 122 languages of Belebele. Published Jev 1.13.0 checkpoint; the rolling latest API alias may change and is not independently pinned by TokenRex. Published source text: Paper abstract: 'Jev reaches 95-99% accuracy on IMDB, SST-2, HellaSwag and ARC and 86.7% on Belebele across 122 languages.'

arXiv — Evaluating and Benchmarking the System One Model Jev
—

No overall score, winner or cost-versus-score frontier is calculated without comparable, attributable benchmark evidence. Different test configurations appear separately. Vendor capabilities are distinct from TokenRex API support.

— means no published value or no matching capability. Provider token limits are not tested gateway guarantees; TokenRex media controls and response formats are listed separately.

Jev 1.13

Sources and verification

Provider specifications describe the upstream model, not a guarantee of every feature through TokenRex. Prices come from the enabled catalog; benchmark results belong to the exact tested model.

Research notes (1)
  • This is a decision model, not a general chat model. The moving latest ID is not a pinned benchmark version.

Popular comparisons

Open the cost calculator →