MyCaptionAI
Introducing Jev 1.13TypeSafe AIReleased September 15, 2026

Jev 1.13

TypeSafe current System One model for fast, structured decisions with typed outputs, probabilities, and confidence.

structured-decisionProprietary APIUSD 0.042 / 1M input tok; output freeContext: 64K (64,000 tokens)
Official Model Card & DocsTry in AI Studio / Playground

Technical Specifications

Architecture Type
System One Model
Total Parameters
Undisclosed
Context Window
64K (64,000 tokens)
Max Output Tokens
Undisclosed
Knowledge Cutoff
Frontier (Current)
Supported Modalities
text, structured-output
License & Access
Proprietary API

Deep Architectural Overview

Jev 1.13 evaluates typed questions against text state and returns structured results for software. It uses a 64K-token request budget and is optimized for calibrated decisions rather than text generation.

Strengths & Considerations

Core Strengths
  • Typed structured decisions
  • Calibrated probabilities and confidence
  • Parallel question evaluation
Known Limitations
  • Text input only
  • Not trained for text generation
  • Best accuracy currently in English

Token & API Pricing

Input Tokens (1M)$0.04
Output Tokens (1M)$0.00
Pricing is verified directly against TypeSafe AI's developer documentation and API rate sheets.

Similar & Alternative Models

Explore other frontier models from TypeSafe AI and comparable reasoning engines.

Browse all models
Anthropic

Introducing Claude Opus 5.5

Anthropic Claude model for long-running agentic coding and knowledge work.

1M ctxUSD 4 / 1M input tok; USD 20 / 1M output tok
September 22, 2026Visit
OpenAI

Introducing GPT-6 Luna

OpenAI GPT-6 model for focused, high-volume workloads where cost efficiency is the priority.

1.05M ctxUSD 0.10 / 1M input tok; USD 0.50 / 1M output tok
September 22, 2026Visit
OpenAI

Introducing GPT-6 Sol

OpenAI GPT-6 model built for complex coding and agentic workflows, balancing intelligence and cost.

1.05M ctxUSD 2 / 1M input tok; USD 10 / 1M output tok
September 22, 2026Visit