gpt-oss-120b in the catalog and in GET /v1/models, sent as model; its current version is gpt-oss-120b-b5c939de. Its page on the site, with its rate history: gpt oss 120b .
Fig. 1, sheet 06 Model and task guides Field Value Type and task language, task chatInputs text Outputs text License and usage conditions apache-2.0
Field Type and task
Value language, task chat
Field License and usage conditions
Value apache-2.0 Limit Value context_tokens131,072 max_output_tokens32,768
Limit context_tokens
Value 131,072
Limit max_output_tokens
Value 32,768 Pool Lanes Precision Certified pool Shared mxfp4 (fp4) Community pool Shared mxfp4 (fp4)
Pool Certified pool
Lanes Shared
Precision mxfp4 (fp4)
Pool Community pool
Lanes Shared
Precision mxfp4 (fp4) On demand, in US dollars per million tokens
Pool Input Cached input Output Certified pool $0.0294 Billed as input $0.147 Community pool $0.0294 Billed as input $0.147
Pool Certified pool
Input $0.0294
Cached input Billed as input
Output $0.147
Pool Community pool
Input $0.0294
Cached input Billed as input
Output $0.147
Sheet 06 of 20
Updated 2026-11-17