Jev Bureau
Ledger Type:Verified Historical Changes

Jev Release & Changes Ledger

This is the permanent, dated ledger of material updates, model releases, provider integrations, and pricing adjustments for Jev.

Every entry in this ledger is verified against authoritative primary documentation. We do not publish speculative future roadmaps or unverified rumors. Current production baseline: jev-1.13.0.

Verified Event Timeline

Chronological (Most Recent First)
Provider Expansion
Source: OpenRouter model directory ↗

OpenRouter Adds Jev Support with Dual Routes

OpenRouter made Jev available to platform developers under model identifier 'typesafe/jev-1.13' and default alias '~typesafe/jev-latest'. OpenRouter lists a 32,000-token context window and matches TypeSafe's published token pricing ($0.042/M input tokens, free output tokens).

Key Specifications & Details:
  • Stable route launched at POST https://openrouter.ai/api/v1/systemone supporting full multi-question batching.
  • Experimental single-decision interface exposed via alpha route at POST https://openrouter.ai/api/alpha/decisions.
Platform Integration
Source: Vercel AI Gateway changelog ↗

Vercel AI Gateway Adds Jev Integration

Vercel AI Gateway announced native provider routing for TypeSafe Jev ('typesafe-ai/jev'). AI SDK 7 exposes Jev through an experimental evaluate API, supporting zero-cold-start decision routing and pass-through key management.

Key Specifications & Details:
  • Exposes Choice, Score, and Boolean evaluation via the AI SDK experimental_evaluate interface.
  • Pass-through authentication to TypeSafe cluster endpoints with zero data retention options.
Model Release
Source: TypeSafe launch announcement by CEO Diogo Almeida ↗

TypeSafe AI Launches Jev 1.13 in Early Access

TypeSafe AI publicly unveiled Jev version 1.13 (versioned ID: 'jev-1.13.0', alias 'jev-latest') as a non-autoregressive System One decision model trained via Reinforcement Learning for Calibrated Decisions (RLCD).

Key Specifications & Details:
  • Introduced three core evaluation primitives: Choice (discrete selection ≤255 choices), Score (ordered rubrics with 2–10 levels returning continuous weighted floats), and Noul (binary proposition truth probability float).
  • Established dual context limits: 64,000 tokens total request budget across state + all questions, with a 32,000-token cap for state + single longest question.
  • Set launch pricing at $0.042 per 1,000,000 input tokens with $0.00 output token billing.
  • Published official SDK packages: 'typesafe_sdk' for Python and '@typesafe-ai/sdk' for TypeScript/JavaScript.

Jev Bureau Ledger Ingestion Policy

Entries are recorded only after public release by TypeSafe AI or authoritative third-party platform providers. Unannounced leaks, unsubstantiated benchmarks, or speculative release timelines are strictly excluded from this ledger.

← Check Current Published PricingGet Started with Direct & OpenRouter APIs →