POST /v1/systemone. The request’s model field selects which one handles the call; see the API reference for the full request shape.
Current models
- Price: Charged per input token. Output tokens are free. A Btok is a billion tokens and an Mtok is a million tokens.
- Rate limits: Measured in tokens per second and requests per minute. A request over either limit returns
429 Too Many Requests. Our client SDKs retry with backoff by default and honor theretry-afterheader when the response carries one. If you call the HTTP API directly, see Handling rate limits. - Context length: Jev ingests the
stateonce and evaluates every question against it in parallel. The 64k budget covers thestateplus all questions combined; the 32k budget applies to thestateplus the single longest question. See Speculative fan-out for packing many questions into one request, and Jev 1.13 jaggedness for how accuracy shifts as the state grows. - Input: Jev evaluates natural-language text. Pre-process non-text inputs (images, audio, video, binaries) into text or structured fields before sending them as
state. See State for supported shapes.
Aliases
An alias is a model name that resolves to a versioned model ID. Send it in themodel field like any other name.
An alias moves when a new release ships, so the answers behind it can change without a change on your side. The response’s
model field reports the versioned ID that answered, so you can log which model produced each result. If you have tuned confidence thresholds against a specific version, pin that version’s ID instead of the alias and move to the new one on your own schedule.
Customizing Jev
Jev is not fine-tuned or LoRA-adapted with customer data. It is trained with RLCD to return calibrated decisions, and the same weights serve every account. You shape its answers to your domain through the request rather than through per-account weights:- Put your proprietary content, records, and reference material in the
statefield. See State. - Encode your domain rules and boundary cases in the
instructionsandcriteriaof each question. See How to build with TypeSafe and Advanced: structure. - Decompose broad judgments into atomic questions and combine the outputs in code. See Composite scoring and the AutoResearch cookbook for training a downstream classical model on Jev’s probabilities.
Language support
Jev accepts natural-language text. English is the primary training language and where accuracy is currently best. Other languages, including CJK scripts, are handled but not equally well; test on your own content before relying on Jev for a non-English workload, and pay close attention to Confidence when routing.Data handling
Jev is not trained on customer requests or responses. See Legal for the Data Processing Agreement, the Privacy Policy, and details on zero data retention (ZDR) for enterprise customers.Listing models
GET /v1/models returns the names your account can send in the model field, with a description and release date for each. It currently lists the aliases. Versioned IDs such as jev-1.13.0 are accepted by the model field whether or not they appear in the list.
array
required
One entry per model or alias.
