gpt-oss-20b
The small, fast sibling of gpt-oss-120b, for high-volume and latency-sensitive tasks.
- Model ID
gpt-oss-20b- Maker
- OpenAI (United States)
- Context
- 30,000 tokens
- Max output
- 30,000 tokens
- Input
- €0.05 per million tokens
- Output
- €0.19 per million tokens
- Tools
- Yes
- JSON mode
- No
- Processing
- In the EU
Example
from openai import OpenAI
client = OpenAI(base_url="https://api.powerspring.eu/v1", api_key="sk-ps-...")
reply = client.chat.completions.create(
model="gpt-oss-20b",
messages=[{"role": "user", "content": "Hello"}],
)
print(reply.choices[0].message.content)