name = "GPT OSS 120B" description = "Open-weight GPT model for self-hosted reasoning and instruction-following workloads" family = "gpt-oss" release_date = "2025-08-05" last_updated = "2025-08-05" attachment = false reasoning = true # Chat `reasoning_effort = low|medium|high`; `medium` is the default. # https://docs.databricks.com/aws/en/machine-learning/model-serving/query-reason-models (accessed 2026-06-25) reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }] temperature = true tool_call = true structured_output = true open_weights = true [cost] input = 0.072 output = 0.28 [limit] context = 131_072 output = 32_768 [modalities] input = ["text"] output = ["text"]