GPT-OSS 120B

OpenAI’s open 120B-parameter model in a mixture-of-experts architecture (only ~5B active per token), served with native MXFP4 quantization. Strong reasoning and a 128K-token window — the largest context in Norlen’s text catalog.

id	gpt-oss-120b
Type	Chat / text
Context	128K tokens
Available on	Starter, Standard, Pro

When to use

• Tasks that require step-by-step reasoning and more depth
• Long documents and conversations (up to 128K context)
• General-purpose assistants with top-tier quality

For short, fast responses, prefer Gemma 4 12B. For code, Qwen3 Coder.

Note

This is a reasoning model: the response may include a thinking step before the final content.

Example

Python

resp = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{"role": "user", "content": "Explain step by step why the sky is blue."}],
)
print(resp.choices[0].message.content)

curl

curl https://api.norlen.io/v1/chat/completions \
  -H "Authorization: Bearer $NORLEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Why is the sky blue?"}]}'

Full parameters in Chat completions.