gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
from openai import OpenAI
client = OpenAI(
base_url="https://infergate.ru/api/v1",
api_key="ig-•••",
)
resp = client.chat.completions.create(
model="openai/gpt-oss-120b",
messages=[{"role": "user", "content": "Привет!"}],
)
print(resp.choices[0].message.content)modelstringобязательныйmessagesarrayобязательныйtemperaturenumbermax_tokensintegertop_pnumbertop_kintegermin_pnumbertop_anumberstopstring | string[]frequency_penaltynumberpresence_penaltynumberrepetition_penaltynumberseedintegerlogit_biasobjectlogprobsbooleantop_logprobsintegerresponse_formatobjectstructured_outputsbooleantoolsarraytool_choicestring | objectreasoningobjectinclude_reasoningboolean