gpt-oss-120b reasoning

openrouter
openai
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...

Capabilities

Context Window 131k tokens
Max Output 131k tokens
Inputs
Outputs

Pricing (per 1M tokens)

Input $0.04
Output $0.17
Cache Read -
Cache Write -

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Move Chat

Select a destination folder:

Move Folder

Select a parent folder:

Folder Settings