Jared Palmer: Kev 4B - API لـمصر، بالجنيه المصري
مباشرkev-4bKev 4B is a small open-weight decision model from Jared Palmer, built as a LoRA adapter and pointer head on Qwen3.5-4B-Base and served over the same /v1/systemone contract as TypeSafe's
Modality
قرار
Context window
8K Tokens
أقصى Output
7K Tokens
المنطقة
US
منشور
30 سبتمبر 2026
الأسعار
Input
2.47
ج.م لكل 1M Tokens
Output
مجاني
ج.م لكل 1M Tokens
مثال على التكلفة الشهرية
123.5 ج.م
تقدير توضيحي: 50M Input tokens و15M Output tokens شهريًا وفق أسعار هذا الـ Model في الكتالوج.
استخدمه عبر واجهة API
Jared Palmer: Kev 4B هو Model قرارات: أرسل المحتوى المطلوب الحكم عليه مع أسئلة محددة النوع (نعم/لا، أو اختيار من متعدد، أو درجة) لتحصل على إجابة محددة النوع لكل سؤال، مع احتمالات حقيقية. استدعِه باستخدام OpenAI SDK على /v1/decisions، أو باستخدام TypeSafe SDK على /v1/systemone مع الـ Base URL https://backend.sovereigneg.com. اقرأ دليل Decisions.
تشغيل خدمات الذكاء الاصطناعي
POST /v1/decisions — Decisions متوافق مع OpenAI: استخدم client.decisions.create في أي OpenAI SDK أو في seg-sdk. ويجيب الـ Model نفسه أيضًا على /v1/systemone عبر TypeSafe SDK.
from seg import SEG # pip install seg-sdk
client = SEG(api_key="YOUR_API_KEY")
decision = client.decisions.create(
model="kev-4b",
input="I paid for my order twice and it still has not arrived after a week.",
questions=[
{
"type": "predicate",
"name": "refund",
"instructions": "Is the customer asking for money back?",
},
{
"type": "choice",
"name": "team",
"instructions": "Which team should handle this?",
"choices": [
{"value": "billing", "description": "Charges, refunds, invoices"},
{"value": "shipping", "description": "Delivery and tracking"},
{"value": "technical", "description": "Bugs and outages"},
],
},
{
"type": "score",
"name": "urgency",
"instructions": "How urgent is this?",
"levels": [{"label": "Can wait"}, {"label": "Handle today"}, {"label": "Handle now"}],
},
],
)
refund, team, urgency = decision.answers
print(refund.probability) # probability of yes, 0-1
print(team.choice) # e.g. "billing"
print(urgency.score) # 0-2, can land between levelsfrom openai import OpenAI
client = OpenAI(api_key="YOUR_API_KEY", base_url="https://backend.sovereigneg.com/v1")
decision = client.decisions.create(
model="kev-4b",
input="I paid for my order twice and it still has not arrived after a week.",
questions=[
{
"type": "predicate",
"name": "refund",
"instructions": "Is the customer asking for money back?",
},
{
"type": "choice",
"name": "team",
"instructions": "Which team should handle this?",
"choices": [
{"value": "billing", "description": "Charges, refunds, invoices"},
{"value": "shipping", "description": "Delivery and tracking"},
{"value": "technical", "description": "Bugs and outages"},
],
},
{
"type": "score",
"name": "urgency",
"instructions": "How urgent is this?",
"levels": [{"label": "Can wait"}, {"label": "Handle today"}, {"label": "Handle now"}],
},
],
)
refund, team, urgency = decision.answers
print(refund.probability) # probability of yes, 0-1
print(team.choice) # e.g. "billing"
print(urgency.score) # 0-2, can land between levelsimport OpenAI from "openai";
const client = new OpenAI({ apiKey: "YOUR_API_KEY", baseURL: "https://backend.sovereigneg.com/v1" });
const decision = await client.decisions.create({
model: "kev-4b",
input: "I paid for my order twice and it still has not arrived after a week.",
questions: [
{
type: "predicate",
name: "refund",
instructions: "Is the customer asking for money back?",
},
{
type: "choice",
name: "team",
instructions: "Which team should handle this?",
choices: [
{ value: "billing", description: "Charges, refunds, invoices" },
{ value: "shipping", description: "Delivery and tracking" },
{ value: "technical", description: "Bugs and outages" },
],
},
{
type: "score",
name: "urgency",
instructions: "How urgent is this?",
levels: [{ label: "Can wait" }, { label: "Handle today" }, { label: "Handle now" }],
},
],
});
const [refund, team, urgency] = decision.answers;
console.log(refund.probability); // probability of yes, 0-1
console.log(team.choice); // e.g. "billing"
console.log(urgency.score); // 0-2, can land between levelscurl https://backend.sovereigneg.com/v1/decisions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kev-4b",
"input": "I paid for my order twice and it still has not arrived after a week.",
"questions": [
{
"type": "predicate",
"name": "refund",
"instructions": "Is the customer asking for money back?"
},
{
"type": "choice",
"name": "team",
"instructions": "Which team should handle this?",
"choices": [
{ "value": "billing", "description": "Charges, refunds, invoices" },
{ "value": "shipping", "description": "Delivery and tracking" },
{ "value": "technical", "description": "Bugs and outages" }
]
},
{
"type": "score",
"name": "urgency",
"instructions": "How urgent is this?",
"levels": [{ "label": "Can wait" }, { "label": "Handle today" }, { "label": "Handle now" }]
}
]
}'الأسئلة الشائعة
كم تكلفة Jared Palmer: Kev 4B؟
2.47 ج.م لكل 1M من Input tokens؛ الـ Output tokens مجانية. يُحتسب الاستخدام لكل Token بالجنيه المصري، بلا أي التزام بحد أدنى.
ما حجم الـ Context window في Jared Palmer: Kev 4B؟
يدعم Jared Palmer: Kev 4B Context window بحجم 8,192 Tokens (8K)، ويُخرج حتى 7,372 Output tokens في الاستجابة الواحدة.
أين يُستضاف Jared Palmer: Kev 4B؟
يُخدَم Jared Palmer: Kev 4B من US (مستضاف في الولايات المتحدة).
كيف أستخدم Jared Palmer: Kev 4B عبر واجهة API؟
Jared Palmer: Kev 4B هو Model قرارات. أرسل المحتوى المطلوب الحكم عليه مع أسئلة محددة النوع (نعم/لا، أو اختيار من متعدد، أو درجة) إلى Endpoint /v1/decisions مع Model ID kev-4b ومفتاح API الخاص بك، باستخدام client.decisions.create في أي OpenAI SDK، أو seg-sdk الخاص بـ SovereignEG، مع الـ Base URL https://backend.sovereigneg.com/v1. ويجيب الـ Model نفسه أيضًا على Endpoint /v1/systemone المتوافق مع TypeSafe، لذا يعمل TypeSafe SDK مع الـ Base URL https://backend.sovereigneg.com.
Models ذات صلة
عرض كل الـ Models ←OpenAI: GPT-6 Luna Decisions
OpenAI · قرار · Context 1M
5.88 ج.م / 1M Input tokens
TypeSafe: Jev 1.13
typesafe · قرار · Context 262K
2.47 ج.م / 1M Input tokens
all-minilm-l12-v2
SBERT · Embedding · Context 512
0.29 ج.م / 1M Input tokens
all-minilm-l6-v2
SBERT · Embedding · Context 512
0.29 ج.م / 1M Input tokens