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 to run on a single H100 GPU with native MXFP4 quantization. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.
openai/gpt-oss-120b is available via Novita's serverless API, where you pay per token. There are several ways to call the API, including OpenAI-compatible endpoints with exceptional reasoning performance.
On-demand deployments allow you to use openai/gpt-oss-120b on dedicated GPUs with high-performance serving stack with high reliability and no rate limits.
Abfragen sofort ausführen, nur für die Nutzung bezahlen
API-Schlüssel erhalten
Registrieren Sie sich und erstellen Sie einen Schlüssel, um den Code unten auszuführen. Die API ist OpenAI-kompatibel.
The API is OpenAI-compatible: point any OpenAI SDK at the base URL and pass this model ID.
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.novita.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="openai/gpt-oss-120b",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=32768,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)