← All models
Hy3
textReasoning
Tencent Hunyuan flagship — 295B MoE with configurable reasoning and grounded, anti-hallucination behavior: answers when grounded, flags missing evidence. 262k context. 100 requests/week free, then from balance.
Pricing
Request / 1M
Response / 1M
Parameters
messagesrequiredreasoning_effortoff · low · medium · hightemperature0–2max_tokensoptionalstreamtrue · falseHow to use via API
from openai import OpenAIclient = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")resp = client.chat.completions.create(model="tencent/hy3",messages=[{"role": "user", "content": "Привет"}],reasoning_effort="low", # off · low · medium · hightemperature=0.7,max_tokens=1024,stream=False,)print(resp.choices[0].message.content)
