1,000 Cerebras — GPT OSS 120B tokens cost $0.00035 as input or $0.00075 as output. Most workloads land in between — a 70/30 input/output split costs about $0.00047. Verified Aug 28, 2026
Quick answer
For Cerebras — GPT OSS 120B, 1,000 tokens cost $0.00035 as input or $0.00075 as output. A representative 70/30 workload is about $0.00047.
Method & trust
The page prices the selected token volume using the model's listed input and output rates, then applies a 70/30 input/output split for the representative workload. Cached input, batch discounts, retries, and provider fees can change the final invoice.
Interactive calculator
1,000 in · 0 out
Input price
$0.35 / 1M tokens
Output price
$0.75 / 1M tokens
Uncached pricing. Add caching and monthly projections in the full calculator.
What 1,000 tokens buys in practice
$0.00043
80% input / 20% output — short replies over conversation history.
$0.00039
90% input / 10% output — long retrieved context, grounded answers.
$0.00037
95% input / 5% output — full documents in, structured extraction out.
Same 1,000 tokens on other models
Related calculations
FAQ
1,000 input tokens cost $0.00035; 1,000 output tokens cost $0.00075. A typical 70/30 input/output mix costs about $0.00047. Rates: $0.35/M input, $0.75/M output.
A chat-style request of ~4,800 tokens (4,000 in + 800 out) means 1,000 tokens is roughly 0.2 requests. For a RAG workload with ~8,500 tokens per request, about 0.1 requests.
Cerebras — GPT OSS 120B has no published cached-input discount on its official pricing page; all input is billed at $0.35/M.