AI article

typesafe/jev fails on OpenRouter chat/completions: how to call it (and the three response shapes that trip people up)

Community description: If you point an OpenAI-style client at OpenRouter and ask for typesafe/jev-1.13, you get this...

Dev.to | Oct 9, 2026 | weirui chen

Automated excerpt

With a TypeSafe key you can skip the gateway: the same state and questions go to TypeSafe's own API, POST https://api. typesafe. ai/v1/systemone, with "model": "jev-latest". "urgency": { "type": "score", "score": 2. 38, "probabilities": { "0": 0, "1": 0. 02, "2": 0. 58, "3": 0. 4 }, "confidence": 0. 58 }, "churn": { "type": "noul", "noul": 0. 96 } "usage": { "input_tokens": 421, "output_tokens": 70, "cost": 0. 000017682 }, $0. 0000177 for three decisions: 421 input tokens at $0. 042 per million. Query GET https://openrouter. ai/api/v1/models? output_modalities=decisions to list every decision model.

Selected automatically from source text; not independently written or fact-checked. Read the original for full context.

Read the original article

Read next

AI briefing: recent picks

More AI news