Tencent: Hy3: AI model
Hy3 is a cost-effective mixture-of-experts model for reasoning and agents from Tencent with a 262K-token context window. Reachable from inside Iran through Hormouz.
- Context window:
- 262,144 tokens
- Input:
- $0.08/1M tokens
- Output:
- $0.33/1M tokens
- Type:
- text
- Tools
- Streaming
- Long context
Thinking levels: high · low · none
Hy3 is Tencent's 295B mixture-of-experts model with 21B active parameters, built for reasoning, agent workflows and production use. It answers directly by default and switches to low or high chain-of-thought for hard maths, coding and multi-step problems. Over a 256K context it tracks references and constraints across many turns and calls tools reliably in different agent frameworks.
It accepts text input and returns text, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters. Hy3 is commonly used for coding, document processing, multi-turn agents, maths and cost-sensitive production workloads. Hormouz serves it behind an OpenAI-compatible API: point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs without changes.
Pricing is usage-based: $0.132 per million input tokens and $0.528 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy3",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Tencent |
|---|---|
| Type | Text |
| Context window | 262,144 tokens |
| Pricing | $0.08/M in · $0.33/M out |
| API | Chat Completions |
| Capabilities | Streaming · Tools |
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tencent/hy3",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="tencent/hy3",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "tencent/hy3",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the Tencent: Hy3 API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches Tencent: Hy3 and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Hy3 cost?
- Pricing is usage-based: $0.132 per million input tokens and $0.528 per million output tokens. There is no fixed monthly fee, and you pay only for the tokens you use.
- How do I access Hy3 from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Hy3 compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Point your base URL at Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
- What context window and capabilities does Hy3 have?
- It has a 262K-token context window, accepts text input, and supports tool calling, structured JSON output and streaming. Reasoning can be switched on when a problem needs more thought and left off when speed matters.
- What is Hy3 good for?
- Typical uses are coding, document processing, multi-turn agents, maths and cost-sensitive production workloads.
Updated 2026-10-13