Tencent
Hy3
tencent/hy3
Hy3 is a 295B-parameter Mixture-of-Experts model with tool calling and configurable reasoning effort (no-think, low, and high modes).
Pricing
| Input | $0.1254per 1M tokens |
|---|---|
| Output | $0.5016per 1M tokens |
| Cached input | $0.0314per 1M tokens read from cache |
Specifications
| Context window | 262Ktokens |
|---|---|
| Max output | 66Ktokens |
| Provider | Tencent |
| Capabilities | Reasoning · Function calling |
| Input types | text |
Use Hy3
Point your existing OpenAI SDK at xKiro and pass tencent/hy3 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",
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
- Kimi K2.5$0.4275
- Kimi K2.6$0.7125
- Kimi K2.7 Code$0.455
- Qwen3 MaxFree
- Qwen3 Omni FlashFree
- Qwen3 VL PlusFree
Call Hy3 through the same endpoints you already use.
Get an API key