Jev glossary
API & ModelsToken usage
Usage
The response field reporting input and output token counts for a request, used for cost tracking.
- Category
- API & Models
- Also known as
- Token usage
- Reading time
- 1 min
- Related terms
- 4
- Directory entries
- 2
- Docs
- docs.typesafe.ai
- Added
- 2026-09-24
Definition
Every response includes usage with input_tokens and output_tokens. Since only input is billed, input_tokens is the number that maps to cost at the published per-billion rate.
The playground also surfaces usage next to probabilities, confidence, and latency, which is how thresholds get tuned against real cost per call.
Tagsapipricing
Related terms
Definitions that connect to this one.
Input tokensThe tokens billed on every request: state plus questions, including speculative questions your code ignores.API & ModelsOutput tokensThe tokens Jev emits for answers; they are reported in usage and are free of charge.API & ModelsToken pricingJev's published rate: $42 per billion input tokens, with output tokens free.API & ModelsPlaygroundThe browser workbench for pasting state and typed questions and inspecting answers, probabilities, confidence, latency, and usage.API & Models
From the Jev directory
Directory entries that go deeper on this term.
The raw HTTP contract behind every SDK: POST a state plus typed noul, choice, and score questions to /v1/systemone, and get one answer per question, with error codes and retry guidance.
Jev Guides & ArticlesDocs#official#docs#api
Official
Browser playground in the TypeSafe console for trying System One: paste state, define typed questions, and inspect answers with probabilities, confidence, latency, and usage.
Jev CookbooksPlayground#official#playground#demos
Official
From the Jev AI model community
Posts from builders shipping with Jev right now.