openai

OpenAI: gpt-oss-120b (batch)

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...

openai/gpt-oss-120b:batch

Context Size

131.072K

Input Price

22,500 pts/M

Output Price

90,000 pts/M

Architecture

Text

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatstopstructured_outputstemperaturetool_choicetoolstop_ktop_p

Details

TokenizerGPT

Max Completion117,964 tokens

Provider Context131.072K tokens

ModeratedNo

CreatedAug 5, 2025