Back to all models
openai
openaiOpenAI: gpt-oss-20b (batch)
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...
openai/gpt-oss-20b:batch
Context Size
131.072K
Input Price
3,600 pts/M221 Ks/M
Output Price
16,800 pts/M1,033 Ks/M
Architecture
Text
Supported Parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Details
TokenizerGPT
Max Completion117,964 tokens
Provider Context131.072K tokens
ModeratedNo
CreatedAug 5, 2025