Jev

Released
2026-09-15
Last refreshed
2026-10-21
Status
Researched 8d ago
ProprietaryCommercial use: restrictedAgentsClassificationJSON / Tool useAgents
TypeSafe AI releases · 1 in the last 12 monthsChangelog →
Specifications
Released
2026-09-15
Context
64K
Specialization
general
Openness
Proprietary
License
ProprietaryRestricted
Weights
Not released
Code
Unknown
Training
Reinforcement Learning
Created by
TypeSafe AI

Machine-native intelligence for software automation.

San Francisco, California, United States
Website
Pricing
Output / 1M
Free
Input / 1M
$0.042

Cheapest of 1 route · TypeSafe AI

Providers(1)
TypeSafe AI
Links
Website

About

Jev is TypeSafe AI's first public System One Model (released 2026-09-15; generally available to everyone with no waitlist as of 2026-09-20 via https://console.typesafe.ai/). First-party docs (https://docs.typesafe.ai/models): current versioned API id jev-1.13.0; aliases jev-latest (SDK default) and jev-preview. Trained with Reinforcement Learning for Calibrated Decisions (RLCD); parallel sampling; structured type-safe outputs with calibrated probabilities and confidence — no free-form string generation; schema matching guaranteed. Docs pricing: input $0.042/MTok ($42 per billion tokens); output tokens free. Context length 64k tokens per request (32k for state plus the longest question). Text input only. Endpoint POST https://api.typesafe.ai/v1/systemone. Proprietary hosted model — no public weights.

Providers(1)

Compare API pricing across 1 tracked provider route for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
TypeSafe AI$0.042Free
Serverless

Capabilities

Structured Outputs

Benchmark peer barsfor Agents

No task-mapped benchmark peers are available for this model yet.

Benchmark scores(2)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionEvaluationSource
JEV Decision Index (0.3)
60.10.3.2Observed 2026-10-17—
Source
ClaimBench
97.72026-10-20Observed 2026-10-20
Evaluator: Vals AI
Notes: Vals AI ClaimBench leaderboard (vals.ai/benchmarks/claimbench, Decision models tab, updated 10/20/2026), rank 8 of 14, 'Jev 1.13.0' accuracy 97.65%; 1,960 claims on 10-K excerpts. Third-party run by Vals AI. Listed entry: Jev 1.13.0.
Source

Migration checks

No linked migration route is available for this model yet.

API versions

jevjev-1.13.0jev-latestjev-previewjev-1.14jev-1.14.0