Last refreshed 2026-10-21. Next refresh: weekly.
Why use Jev on TypeSafe AI?
TypeSafe AI offers Jev with pay-as-you-go pricing at $0.04/1M input tokens. First-party TypeSafe AI hosted inference for System One Models (Jev).
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: jev-1.13.0jev-1.13.0Request example
jev-1.13.0.Gotchas
- Use provider model ID "jev-1.13.0", not the LLMReference slug "jev".
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.04 |
| Output tokens | Free |
Capabilities
About Jev
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.