Description
gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for lower-latency inference and deployability on consumer or single-GPU hardware. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.
API Usage Examples
OpenAI Compatible Endpoint
Use this endpoint with any OpenAI-compatible library. Model: OpenAI: gpt-oss-20b (openai/gpt-oss-20b)
curl https://api.ridvay.com/v1/chat/completions -H "Content-Type: application/json" -H "Authorization: Bearer YOUR_API_KEY" -d '{
"model": "openai/gpt-oss-20b",
"messages": [
{
"role": "user",
"content": "Explain the capabilities of the OpenAI: gpt-oss-20b model"
}
],
"temperature": 0.7,
"max_tokens": 1024
}'Supported Modalities
- Text
API Pricing
- Input: 0.04$ / 1M tokens
- Output: 0.15$ / 1M tokens
Token Limits
- Max Output: 131,000 tokens
- Max Context: 131,000 tokens
Subscription Tiers
- free
- pro
- ultimate