Models

​

Current models

• Price: You pay per input token. Output tokens are free. A Btok is a billion tokens and an Mtok is a million tokens.
• Context length: Two limits, the per-request context and the per-question context. See Context length. To raise both, see Long context.
• Input: Jev reads natural-language text, sent as a string, a JSON object, or an array of text values. It does not accept audio or video. Convert those into text or structured fields before you send them as state. See State for the shapes state accepts.

​

Context length

• Per-request context (per_request_context): the state plus all questions combined.
• Per-question context (per_question_context): the state plus any one question.

​

Long context

curl https://api.typesafe.ai/v1/systemone \
  -H "Authorization: Bearer $TYPESAFE_API_KEY" \
  -H "Content-Type: application/json" \
  -H "TypeSafe-Danger-Zone-Long-Context: true" \
  -d '{
    "model": "jev-latest",
    "state": "<a long contract, transcript, or record>",
    "questions": {
      "has_termination_clause": {
        "type": "noul",
        "instructions": "Does the `state` include a clause that lets either party end the agreement early?"
      }
    }
  }'

​

Rate limits

​

Aliases

​

Customizing Jev

• Put your proprietary content, records, and reference material in the state field. See State.
• Encode your domain rules and boundary cases in the instructions and criteria of 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

​

Data handling

​

Listing models

curl https://api.typesafe.ai/v1/models \
  -H "Authorization: Bearer $TYPESAFE_API_KEY"

from typesafe_sdk import TypeSafeClient

with TypeSafeClient() as client:
    for model in client.models.list().models:
        print(model.name, model.release_date, model.description)

import { TypeSafeClient } from "@typesafe-ai/sdk";

const client = new TypeSafeClient();
const models = await client.models.list();
for (const model of models) {
  console.log(model.name, model.release_date, model.description);
}