Cerebras pricing overview
TokenWatch tracks 2 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-120b at $0.350 per million input tokens and $0.750 per million output tokens. 2 of 2 text models publish a cache-read price; 2 carry a zero-data-retention tag.
Cerebras text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| openai | cerebras | OpenAI: gpt-oss-120b | $0.350 | $0.750 | $0.350 | $0.352 |
| qwen | cerebras | Qwen: Qwen3.8 27B | $0.990 | $1.49 | $0.990 | $0.993 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.