GPT-OSS 120B

gpt-oss-120b-medium

INPUT / 1M$0.022

OUTPUT / 1M$0.108

CACHE-READ / 1M—dieses Modell unterstützt kein Caching

KONTEXT128KTokens pro Request

Modell aufrufen

from openai import OpenAI

client = OpenAI(
    api_key="sk-ak-...",
    base_url="https://apikey.sh/v1",
)

resp = client.chat.completions.create(
    model="gpt-oss-120b-medium",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)

Spezifikationen

AnbieterOpenAI (open weights)

KategorieSchnell & günstig

Kontext128K tokens

Max. Output32.0K

Endpoint/v1/chat/completions

toolsstreaming