Hy3 with Jev
Hy3 is a model from Tencent, released 2026-07-06. It costs $0.132 per million input tokens and $0.528 per million output tokens, reads up to 262K tokens of context, and writes up to 128,000 tokens in one reply. Through llm11, set model to tencent/hy3.
- Input price
- $0.132 / 1M
- Output price
- $0.528 / 1M
- Context window
- 262K tokens
- Max output
- 128K tokens
- Cached input
- $0.033 / 1M
- Released
- 2026-07-06
- Accepts
- text
Read from the provider's prompt cache
Read from the live catalogue and refreshed daily. At blended list price, 75% of the 332 priced models we can call cost more.
Using Hy3 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. Hy3 does the answering when Jev sends it work, or when you name it yourself. At list price Hy3 falls in the llm11-fast 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/hy3 as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Hy3 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 | $0.00017 | $0.172 |
| Question over retrieved documents | 4,000 / 500 | $0.00079 | $0.792 |
| Long document summary | 30,000 / 1,000 | $0.00449 | $4.49 |
Cheaper models to try
The catalogue has no benchmark score for Hy3, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Qwen Qwen3.8 Omni Flash | $0.150 | $0.470 | 1M | |
| Qwen Qwen3.8 Flash | $0.150 | $0.470 | 1M | |
| Qwen Qwen3 30B A3B | $0.120 | $0.500 | 131K | |
| Qwen Qwen3 VL 8B InstructRetires 2026-10-09 | $0.117 | $0.455 | 262K |
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/hy3",
messages=[{"role": "user", "content": "Hello"}],
)More from Tencent
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Hy4 preview | $0.834 | $2.50 | 1.05M | |
| 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 preview | $0.180 | $0.600 | 262K | |
| Hunyuan A13B Instruct | $0.140 | $0.570 | 131K |
Questions
- What is Hy3 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. Hy3 does the answering when Jev sends it work, or when you name it yourself. At list price Hy3 falls in the llm11-fast 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/hy3 as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Hy3 a System One model?
- No. Hy3 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 Hy3 cost?
- $0.132 per million input tokens and $0.528 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00079, so a thousand of them is about $0.792. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Hy3 context window?
- 262,144 tokens, with up to 128,000 tokens in a single reply.
- Does Hy3 support tool calling and structured output?
- The catalogue lists tool calling, structured output and reasoning controls.
- Can I use Hy3 through llm11?
- Yes. Set model to tencent/hy3 on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Hy3?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Hy3 falls in the llm11-fast 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/hy3 as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Hy3?
- Nearest in price and below it: Qwen Qwen3.8 Omni Flash at $0.150 in and $0.470 out, Qwen Qwen3.8 Flash at $0.150 in and $0.470 out and Qwen Qwen3 30B A3B at $0.120 in and $0.500 out. The catalogue has no benchmark score for Hy3, so this is a price ordering. It does not claim these answer as well.