> ## Documentation Index
> Fetch the complete documentation index at: https://composio-preview.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Jev

> Jev is TypeSafe AI's System One API for discovering available models and evaluating structured state with Noul, Choice, and Score questions.

![Jev logo](https://mintcdn.com/composio-preview/tIuAovF9-7pXq2wA/images/toolkits/jev.svg?fit=max\&auto=format\&n=tIuAovF9-7pXq2wA\&q=85\&s=6fbfab162baf7ef633573b0a6532d3b4)

* **Category:** artificial intelligence
* **Auth:** API\_KEY
* **Composio-managed OAuth available?** N/A
* **Tools:** 2
* **Triggers:** 0
* **Slug:** `JEV`
* **Version:** 20261101\_00
* **Instant:** Supported on the latest version. Support varies by tool.

## Tools

> [accordion] Evaluate State
>
> **Slug:** `JEV_EVALUATE_STATE`
>
> Evaluate one shared state against one or more named Noul, Choice, or Score questions in parallel; each call performs usage-priced inference.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** \$0.042 per 1 million input tokens; output tokens free
>
> #### Input Parameters
>
> **model** `string`
>
> Available model name or alias. Defaults to jev-latest; use JEV\_LIST\_MODELS to discover account-specific alternatives.
>
> **state** `string` *required*
>
> Content to evaluate and share across every question in this call. May be text, a JSON object, or a JSON array.
>
> **questions** `object` *required*
>
> Non-empty map from caller-chosen question names to Noul, Choice, or Score definitions. The same names key the returned answers.
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not

> [accordion] List Models
>
> **Slug:** `JEV_LIST_MODELS`
>
> List Jev model names and aliases returned for the connected account. Versioned model IDs may be accepted for evaluations even if they are not listed.
>
> **Instant:** Supported on the latest version.
>
> **Instant pricing:** 0
>
> #### Output
>
> **data** `string` *required*
>
> Data from the action execution
>
> **error** `string`
>
> Error if any occurred during the execution of the action
>
> **successful** `boolean` *required*
>
> Whether or not the action execution was successful or not
