Jev 1.13
typesafe/jev-1.13Jev 1.13 (typesafe/jev-1.13) is a decision model from TypeSafe with a 64,000-token context window, priced at $0.04/1M input and $0.00/1M output tokens. Returns predicate, choice, or score answers via the haimaker.ai decision API.
Overview
Jev 1.13 is a decision model by TypeSafe. It returns structured predicate, choice, or score answers through the non-streaming decision API. It supports a 64K token context window.
Features & Capabilities
| Mode | Decisions |
| Context Window | 64,000 tokens |
| Function Calling | Not supported |
| Vision | Not supported |
| Reasoning | Not supported |
| Web Search | Not supported |
| Url Context | Not supported |
API Usage
Send text or structured JSON with 1–128 questions to /v1/decisions. Questions request predicate, choice, or score answers. Responses are non-streaming. For state-based requests, use /v1/systemone with state and a named questions object.
import requests
response = requests.post(
"https://api.haimaker.ai/v1/decisions",
headers={"Authorization": "Bearer YOUR_API_KEY"},
json={
"model": "typesafe/jev-1.13",
"input": "Please refund my duplicate payment.",
"questions": [{
"type": "predicate",
"name": "needs_refund",
"instructions": "Is the customer requesting a refund?"
}],
},
timeout=30,
)
response.raise_for_status()
print(response.json()["answers"])Frequently Asked Questions
What is the context window of Jev 1.13?
Jev 1.13 (typesafe/jev-1.13) has a 64,000-token context window.
How much does Jev 1.13 cost?
Jev 1.13 is priced at $0.04 per 1M input tokens and $0.00 per 1M output tokens when accessed via the haimaker.ai decision API.
How do I use Jev 1.13 via API?
Send a non-streaming POST to https://api.haimaker.ai/v1/decisions with model "typesafe/jev-1.13", input (text or structured JSON), and a questions array. Questions can request predicate, choice, or score answers; read the answers field in the response. Alternatively, POST to https://api.haimaker.ai/v1/systemone with state and a named questions object for noul, choice, or score answers. Authentication uses a Bearer API key from https://app.haimaker.ai.
What does Jev 1.13 return?
Decision models return structured predicate, choice, or score answers instead of chat messages. The decision API accepts 1–128 questions per request and supports text and structured JSON inputs. Responses are non-streaming.
Use Jev 1.13 with the haimaker API
Returns predicate, choice, or score answers via the haimaker.ai decision API.