Typesafe: Jev

System One model for fast, typed probabilistic decisions over text or structured state

Model lab: Typesafe
Model family: —

Modalitiestext → text

Context window64,000

Maximum output—

InputUSD 0.0336 / 1M tokens

Try now View docs

Quickstart

Use your Moduck API Key, set the API base URL to https://api.moduck.ai/v1, and set the model parameter to typesafe/jev-latest.

import os
import requests

base_url = "https://api.moduck.ai/v1"
api_key = os.environ["MODUCK_API_KEY"]
model_id = "typesafe/jev-latest"

response = requests.post(
    f"{base_url}/chat/completions",
    headers={
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
    },
    json={
        "model": model_id,
        "messages": [{"role": "user", "content": "Hello!"}],
        "stream": False,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json())

Use the familiar OpenAI-style chat request format to make model integration easier.

Jev API Pricing

Type	Price information
Input	USD 0.0336 / 1M tokens

Performance

Measured on the Moduck gateway across live traffic, hour by hour over the last 24 hours. Time to first token is how long before anything appears; throughput is how fast the answer is written after that; end-to-end latency is the whole round trip. Figures are medians unless the card says otherwise.

Performance trends

Request throughput14.3 requests/minCurrent

Queue wait0.9 sCurrent

Completion time6.5 sCurrent

Request throughput

Current14.3 requests/min

Window average15.0 requests/min

Queue wait

Current0.9 s

Window average0.9 s

Completion time

Current6.5 s

Window average6.0 s

Tail completion time (P99)

Current14.1 s

Window average13.8 s

Retry rate

Current0.7%

Window average1.0%

Error rate

Current0.0%

Window average0.1%

Availability

Uptime is the share of time at least one provider serving this model responded. Availability is stricter: the share of requests actually served. A provider that answers but fails part of the traffic lowers availability without lowering uptime. Both cover the last three days.

Uptime100%At least one provider responded

Availability100%Requests actually served

Error rate0%Share of failed requests

Served requests, hour by hour

24 hours agoNow

Jev Compare models

Model	Input price	Output price	Context window	Capabilities
JevThis page	USD 0.0336 / 1M tokens	Not billed on output	64,000	Specialized model
Jev 1.14	USD 0.0336 / 1M tokens · Context ≤ 32000 tokens	Not billed on output	64,000	Specialized model
Drex 2.0	USD 0.048 / 1M tokens	Not billed on output	131,072	Specialized model
Liquid d1	USD 0.016 / 1M tokens	Not billed on output	65,536	Specialized model
Drex 1.5	USD 0.032 / 1M tokens · Context ≤ 131072 tokens	Not billed on output	139,264	Specialized model

Model specifications

Input: text
Output: text
Context window: 64,000
Maximum output: —
Release date: 2026-09-15
Attachments: No
Reasoning: No
Tool calling: No
Structured output: Yes
Temperature setting: No
Open weights: No

Frequently asked questions

What is Jev for?

System One model for fast, typed probabilistic decisions over text or structured state

What inputs and outputs does Jev support?

Recorded inputs: text; outputs: text.

How is Jev priced?

The pricing table shows the current recorded Moduck price. For example: Input USD 0.0336 / 1M tokens. See the pricing table for all units, variants, and conditions.

What specifications are recorded for Jev?

Current model records list Context window 64,000 tokens.

What model parameter does the Quickstart use?

The example uses typesafe/jev-latest. This value comes from the page identifier and is not confirmed as a callable Moduck public ID.

Can I call this model through the Moduck API now?

This page has no verified Moduck API call for this model. A Quickstart example or reserved ID does not establish access; check the models available to your account.