Tencent
Hy3 Preview
tencent/hy3-preview
Hy3 Preview is an early-access build of the Hy3 model, with tool calling and configurable reasoning levels.
Pricing
| Input | $0.18per 1M tokens |
|---|---|
| Output | $0.6per 1M tokens |
| Cached input | $0.06per 1M tokens read from cache |
Specifications
| Context window | 192Ktokens |
|---|---|
| Max output | 64Ktokens |
| Provider | Tencent |
| Capabilities | Reasoning · Function calling |
| Input types | text |
Use Hy3 Preview
Point your existing OpenAI SDK at xKiro and pass tencent/hy3-preview as the model. Nothing else in your code changes.
from openai import OpenAI
client = OpenAI(
base_url="https://api.xkiro.com/v1",
api_key="YOUR_XKIRO_KEY",
)
response = client.chat.completions.create(
model="tencent/hy3-preview",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Supported parameters
max_tokens · temperature · top_p · stop · frequency_penalty · presence_penalty · seed · stream · tools · tool_choice · response_format · structured_outputs · reasoning · include_reasoning
Related models
Call Hy3 Preview through the same endpoints you already use.
Get an API key