Your privacy choices

Allow optional cookies for referral attribution, visit analytics, and Google Ads purchase measurement.

Model selection and API access

Jev(preview) API pricing and integration guide

Review the Jev preview decision alias, typed outputs, question types, and checks for preview behavior.

Current prices and model reference

Model ID
jev-preview
Documented context
64K
Documented image input
—

Live pricing or availability cannot be confirmed right now. Check the model catalog before making a request.

Prices are in CNY. A 1× multiplier equals CNY 0.4 per million input tokens. Output and cache charges follow the billing configuration; your usage record is authoritative.

View the full live pricing catalog

When to consider this model

Use it only when preview behavior is intentional, for low-risk experiments and threshold calibration rather than a pinned production route.

How to evaluate it

Run jev-preview and jev-1.13.0 on the same sample set. Record the response model, probabilities, latency, and billing before comparing thresholds.

What to check before integration

Use the exact jev-preview ID. The official page currently shows it pointing to the same version as jev-latest; aliases can move, so recheck before production use.

Client configuration

In a client supporting a custom API endpoint, enter this base URL and model ID with your own API key. Select the protocol described in the client tutorial and validate a short request first.

Base URL: https://api.llm-token.cn/v1
Model ID: jev-preview