Tencent Hy4 Preview
Tencent Hy4 Preview is an early version of the next model in Tencent's Hy line, published as a preview. Through our API it takes text, reasons before answering, calls tools and returns structured output over a context of up to a million tokens. A preview may change or be withdrawn by the developer — keep that in mind before you build on it. It is served by a third-party inference provider through our partner, not on Heabsy hardware: the same key and the same invoice, but no zero data retention, and the request may be processed outside the EEA.
model id: hy4-preview
from openai import OpenAI client = OpenAI( api_key="hb-...", base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create( model="hy4-preview", messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)
curl https://api.heabsy.com/v1/chat/completions \ -H "Authorization: Bearer $HEABSY_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "hy4-preview", "messages": [{"role": "user", "content": "Hello"}] }'
import OpenAI from "openai"; const client = new OpenAI({ apiKey: process.env.HEABSY_API_KEY, baseURL: "https://api.heabsy.com/v1",}); const r = await client.chat.completions.create({ model: "hy4-preview", messages: [{ role: "user", content: "Hello" }],});console.log(r.choices[0].message.content);
Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n
Models we run ourselves, behind the same key
Tencent Hy4 Preview on this page is partner-hosted: no zero data retention, and the provider handles the request under its own policy. The same API key also reaches models we serve on our own GPUs without storing prompts or completions — Qwen3.8 27B for coding and agents, which also runs Claude Code through our Anthropic-compatible endpoint, and MiMo V2.6 Flash with a million-token context.
Our flagship for coding, agents and documents; every speed figure on this site was measured on it.
Xiaomi's agent model with a million-token context, image input, reasoning and tool calling.
Price list, updated 30 October 2026. No minimum spend, no subscription.
Technical details
- Context window
- 1M tokens
- Max output
- 64,000 tokens
- Throughput limit
- —
- Tokenizer
- Other
- Streaming
- yes
- Open weights
- —
- max_tokens
- 1 … 64000
This model is served by a third-party inference provider through our partner, not on Heabsy hardware. You keep one key and one invoice from an EU company, but there is no zero data retention: the provider handles the request under its own policy, and processing may take place outside the EEA. For personal or regulated data, use a model on Heabsy hardware.
Questions about this model
›Where is Tencent Hy4 Preview computed?
At a third-party inference provider that serves this model through our partner, outside our own infrastructure. Where exactly the request is computed is not fixed and may be outside the EEA. The contract and the invoice stay with our EU company.
›Does Tencent Hy4 Preview store prompts and completions?
There is no zero-data-retention guarantee for this model: the request goes to a third-party provider, which handles it under its own policy and may keep logs. For personal or regulated data, use a model on Heabsy hardware.
›How large is the Tencent Hy4 Preview context window?
1M tokens, with up to 64,000 tokens of output.
›What does Tencent Hy4 Preview cost?
$1.668 per million input tokens and $5.002 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.
›Is there a throughput limit on Tencent Hy4 Preview?
The catalog does not report a throughput limit for this model.
Compare with similar models
| Model | Developer | Parameters | Context | Licence | Input / 1M |
|---|---|---|---|---|---|
| Tencent Hy4 Preview | Tencent | — | 1M | — | $1.668 |
| GPT-6 Luna | OpenAI | — | 1M | — | $0.12 |
| GLM 5.3 Flash | Z.ai | 320B / 18B | 1M | MIT | $0.20 |
| GPT-5.6 Luna | OpenAI | — | 1M | — | $0.24 |
36 more models behind the same key and the same invoice.
Browse the catalog