Tencent: Hy3 preview - API in Egypt, billed in EGP
Livehy3-previewHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled, low, and high modes, allowing it to
Modality
Chat
Context window
262K tokens
Max output
236K tokens
Region
US
Published
29 Sept 2026
Pricing
Input
10.31
EGP per 1M tokens
Output
34.38
EGP per 1M tokens
Monthly cost example
1,031.43 EGP
Illustrative estimate: 50M input + 15M output tokens per month at this model's catalog rates.
Use it via the API
Tencent: Hy3 preview works with any OpenAI-compatible SDK — point the base URL at https://dev-backend.sovereigneg.com/v1 and use your SovereignEG API key.
Run inference
OpenAI-compatible — POST /v1/chat/completions — drop-in for any OpenAI SDK.
from openai import OpenAI
client = OpenAI(
base_url="https://dev-backend.sovereigneg.com/v1",
api_key="YOUR_API_KEY",
)
response = client.chat.completions.create(
model="hy3-preview",
messages=[
{"role": "user", "content": "What are some fun things to do in Cairo?"}
],
)
print(response.choices[0].message.content)import OpenAI from "openai"
const client = new OpenAI({
baseURL: "https://dev-backend.sovereigneg.com/v1",
apiKey: "YOUR_API_KEY",
})
const response = await client.chat.completions.create({
model: "hy3-preview",
messages: [
{ role: "user", content: "What are some fun things to do in Cairo?" },
],
})
console.log(response.choices[0].message.content)curl https://dev-backend.sovereigneg.com/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "hy3-preview",
"messages": [
{"role": "user", "content": "What are some fun things to do in Cairo?"}
]
}'Frequently asked questions
How much does Tencent: Hy3 preview cost?
10.31 EGP per 1M input tokens; 34.38 EGP per 1M output tokens. Billing is metered per token in Egyptian pounds (EGP), with no minimum commitment.
What is the context window of Tencent: Hy3 preview?
Tencent: Hy3 preview supports a context window of 262,144 tokens (262K), with up to 235,929 output tokens per response.
Where is Tencent: Hy3 preview hosted?
Tencent: Hy3 preview is served from US (US-hosted inference).
How do I use Tencent: Hy3 preview via the API?
Tencent: Hy3 preview is available through the OpenAI-compatible SovereignEG API: point your SDK's base URL at https://dev-backend.sovereigneg.com/v1 and call /v1/chat/completions with model "hy3-preview" and your API key.
Related models
View all models →Tencent: Hunyuan A13B Instruct
tencent · Chat · 131K context
8.02 EGP / 1M input tokens
Tencent: Hy-MT2-1.8B
tencent · Chat · 8K context
2.52 EGP / 1M input tokens
Tencent: Hy-MT2-30B-A3B
tencent · Chat · 8K context
4.24 EGP / 1M input tokens
Tencent: Hy-MT2-7B
tencent · Chat · 8K context
4.24 EGP / 1M input tokens