← All models
Tencent: Hy3
tencent/hy3textReasoning
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.
Price in / out
Cache, read / write
Context / Max output
262K / 128K
Released
Jul 6, 2026
Additional rates
During some UTC hours the upstream charges 1.6× more — per-route rates are in the table below.
Parameters
messagesrequiredreasoning_effortoff · low · medium · highmax_tokensoptional · alias max_completion_tokensstreamtrue · falsetoolsfunction calling (OpenAI format)tool_choiceauto · none · requiredresponse_formatjson_object · json_schemaweb_search · · · providerrouting: order · only · ignore · sortstream_options{"include_usage": true}Fine-tuning · 9
temperature0–2stopoptionalseedoptionaltop_p0–1top_koptionalmin_p0–1frequency_penalty−2…2presence_penalty−2…2repetition_penalty0–2How to use via API
from openai import OpenAI
client = 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 · high
temperature=0.7,
max_tokens=1024,
stream=False,
)
print(resp.choices[0].message.content)
# Стриминг: stream=True — ответ приходит чанками
for chunk in client.chat.completions.create(
model="tencent/hy3",
messages=[{"role": "user", "content": "Привет"}],
stream=True,
):
print(chunk.choices[0].delta.content or "", end="", flush=True)
