Hy4 preview with Jev
Hy4 preview is a model from Tencent, released 2026-08-28. It costs $0.834 per million input tokens and $2.50 per million output tokens, reads up to 1.05M tokens of context, and writes up to 64,000 tokens in one reply. Through llm11, set model to tencent/hy4-preview.
- Input price
- $0.834 / 1M
- Output price
- $2.50 / 1M
- Context window
- 1.05M tokens
- Max output
- 64K tokens
- Cached input
- $0.042 / 1M
- Released
- 2026-08-28
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 36% of the 332 priced models we can call cost more.
Using Hy4 preview with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Hy4 preview does the answering when Jev sends it work, or when you name it yourself. At list price Hy4 preview falls in the llm11-balanced band, but no pack routes to it because Tencent is not one of the labs the packs draw from. You can still pin it: pass tencent/hy4-preview as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Hy4 preview with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00092 | $0.917 |
| Question over retrieved documents | 4,000 / 500 | $0.00459 | $4.59 |
| Long document summary | 30,000 / 1,000 | $0.028 | $27.52 |
Cheaper models to try
The catalogue has no benchmark score for Hy4 preview, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| SpaceXAI Grok Build 0.1 | $1.00 | $2.00 | 256K | |
| DeepSeek DeepSeek V4 Pro 0423 | $0.936 | $1.87 | 1.05M | |
| DeepSeek R1 | $0.700 | $2.50 | 64K | |
| Google Gemini 3 Flash Preview | $0.500 | $3.00 | 1.05M |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="tencent/hy4-preview",
messages=[{"role": "user", "content": "Hello"}],
)More from Tencent
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Hy-MT2-1.8B | $0.044 | $0.177 | 8K | |
| Hy-MT2-30B-A3B | $0.074 | $0.295 | 8K | |
| Hy-MT2-7B | $0.074 | $0.295 | 8K | |
| Hy3 | $0.132 | $0.528 | 262K | |
| Hy3 preview | $0.180 | $0.600 | 262K | |
| Hunyuan A13B Instruct | $0.140 | $0.570 | 131K |
Questions
- What is Hy4 preview with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Hy4 preview does the answering when Jev sends it work, or when you name it yourself. At list price Hy4 preview falls in the llm11-balanced band, but no pack routes to it because Tencent is not one of the labs the packs draw from. You can still pin it: pass tencent/hy4-preview as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Hy4 preview a System One model?
- No. Hy4 preview answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Hy4 preview cost?
- $0.834 per million input tokens and $2.50 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00459, so a thousand of them is about $4.59. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Hy4 preview context window?
- 1,048,576 tokens, with up to 64,000 tokens in a single reply.
- Does Hy4 preview support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Hy4 preview through llm11?
- Yes. Set model to tencent/hy4-preview on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Hy4 preview?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Hy4 preview falls in the llm11-balanced band, but no pack routes to it because Tencent is not one of the labs the packs draw from. You can still pin it: pass tencent/hy4-preview as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Hy4 preview?
- Nearest in price and below it: SpaceXAI Grok Build 0.1 at $1.00 in and $2.00 out, DeepSeek DeepSeek V4 Pro 0423 at $0.936 in and $1.87 out and DeepSeek R1 at $0.700 in and $2.50 out. The catalogue has no benchmark score for Hy4 preview, so this is a price ordering. It does not claim these answer as well.