LLM & ChatActive
openai / gpt-oss-20b
gpt-oss-20b
OpenAI GPT-OSS-20B model.
ChatLLMRAGReasoningBf16
Model ID
gpt-oss-20b
Provider
openai
Added
1756388844
wiro playground—openai/gpt-oss-20b
Added 1756388844
openai/gpt-oss-20b is a 21B parameter open-weight model with 3.6B active parameters, designed for lower-latency and specialized use cases. Released under the Apache 2.0 license, it supports configurable reasoning effort, fine-tuning, and agentic capabilities such as function calling, web browsing, Python execution, and structured outputs. Trained with the harmony response format and optimized with MXFP4 quantization, it runs efficiently within 16GB of memory, making it suitable for local deployment and customization across diverse applications.
API quick start
Run gpt-oss-20b with a single API call.
POST https://api.wiro.ai/v1/Run/openai/gpt-oss-20b
{
"prompt": "Explain quantum mechanics clearly and con…",
"user_id": "...",
"session_id": "...",
"system_prompt": "You are a helpful, respectful and honest …"
}