openaiUnknownfree endpoint
gpt-oss-20b
openai/gpt-oss-20b
Smaller Mixture of Experts (MoE) text-only LLM for efficient AI reasoning and math
Context Length
131,072 tokens
Input Pricing
Not published
Output Pricing
Not published
Recent Latency
No probes
Model Architecture & Limits
Canonical IDopenai/gpt-oss-20b
Publisher / Originatoropenai
Model FamilyNot published
ArchitectureTransformer <br> (Mixture-of-Experts (MoE) <br>)
Context Window Limit131,072 tokens
Max Output Tokens4,096 tokens
Endpoint Protocolopenai-chat
Capabilities & Modal Surfaces
Chat Conversation✓ Yes
Tool / Function Calling✕ No
Reasoning / Thinking✓ Yes
Structured Output (JSON)✓ Yes
Vision / Multimodal✕ No
Audio Processing✕ No
License & Restrictions
NVIDIA API Trial Terms of Service
Commercial and research use permitted under governing model and API terms.