open jev models and compatible apis

“Open Jev” Can Describe Several Different Things

These claims form no automatic ladder. Public weights can lack training data; a compatible endpoint can remain hosted and closed; a reimplementation can share primitives while behaving very differently.

Treat Community Projects as Named Implementations

Perplexity publishes a Decisions API and model card. Laya, Kev-9B, Intern-Decision and Julia 1 publish separate model cards and local paths. Eric Zhang’s openjev-sglang repository now identifies his earlier experiment and directs users to SGLang’s native decisions endpoint. None of these models is a TypeSafe release unless TypeSafe explicitly says so.

When a repository is available, record its owner, commit, license, model artifact and last activity. Avoid the generic phrase “open Jev” in benchmark charts; use the exact implementation and checkpoint name.

Named Independent Projects Checked October 2, 2026

Ollama lists Nimble and Tev1 with a local /v1/systemone call and requires Ollama 0.35 or later for each. Its listed context windows describe serving limits, not validated decision quality at that length. This is an artifact and provenance inventory, not a quality leaderboard. The dated launch roundup separates hosted APIs from independent models and local runtimes.

Test the Protocol Before Testing Model Quality

Protocol compatibility reduces integration effort. It says nothing yet about calibration or semantic accuracy. Keep a conformance suite separate from the evaluator benchmark.

• Does the server accept the same state types and primitive definitions?
• Are Choice criteria, Score levels and Noul answers encoded the same way?
• Do distributions normalize and expose the same fields?
• Are batching, limits and error semantics compatible?
• Does the client require adapter logic that changes the evaluation?

Build Conformance Fixtures Around Observable Behavior

A conformance suite should use synthetic inputs and assert schema and failure behavior, not demand identical probabilities. Preserve native responses beside the normalized representation so a parser bug is distinguishable from a model disagreement. The HTTP API guide defines the direct observable contract and error handling covers retry boundaries.

Evaluate Behavioral Substitution on Identical Evidence

Run TypeSafe Jev and each alternative on blind held-out labels with equivalent questions and state. Compare class errors, full distributions, calibration, repeatability, language slices, adversarial cases, throughput and total cost. Pin the hosted provider and open checkpoint.

Do not copy thresholds between implementations. Even when both return 0.8, the empirical error associated with that number may differ. The benchmark protocol defines the required reporting.

A Substitution Report Needs More than Agreement

Raw agreement with Jev is not ground truth: two systems can agree and both be wrong. Score each against blind labels or downstream outcomes first, then use disagreement analysis to explain differences. Publish the exact checkpoint, quantization, runtime, hardware, provider region and date so another team can reproduce the result.

Open Deployment Changes the Risk Owner

Use Precise Language in Public Comparisons

• Say “Jev-compatible API” only after conformance testing.
• Say “System One-inspired” when the project adopts the interface idea.
• Say “open weight” only when weights and their license are available.
• Never attribute community benchmarks to TypeSafe Jev without running TypeSafe Jev.
• Publish the exact commit, checkpoint, provider and date.