Cerebras Inference GPT OSS model page (first-party PayGo price and vendor speed)

Fetched 2026-10-17 as the markdown rendering of the model page (the HTML docs shell did not extract). Model ID gpt-oss-120b. Pricing table, USD per 1M tokens: Input $0.35, Output $0.75, on both the Free tier and the Pay as you go tier. Speed (tokens/sec) ~3000. Context length 65k on the Free tier and 131k on Pay as you go. This is the first first-party price for the representative model; the 2026-10-14 seed recorded $0.35/$0.75 from third-party price trackers because the public pricing page did not extract a per-model rate table. The numbers did not move.