gpt-oss-120b
A Cerebras model. Every figure below was read off Cerebras's own pricing page and stamped with the date it was read — last pass 2026-08-04. Nothing here is estimated.
| Input / 1M tokens | $0.35 |
| Output / 1M tokens | $0.75 |
| Vendor-quoted tokens/sec | 3000 |
Price is only one decision input. Runtime performance requires reproducible measurement; the benchmark protocol explains what is measured and clearly marks results that are still pending. See every Cerebras model on its provider page.