[Update] Deprecation of llama-4-maverick-17b-128e-instruct (Preview Model)

Explore new models for uninterrupted service.

Hi there,   We are reaching out to inform you that the llama-4-maverick-17b-128e-instruct (Preview Model) will be officially deprecated from Cerebras Cloud API as of Oct 15, 2025. This decision is part of our ongoing efforts to provide you with the most up-to-date models on our platform, including models in preview that we update even more regularly.   What this means for you: You’ll be able to use llama-4-maverick-17b-128e-instruct until Oct 15, 2025. After this date, your API calls with the deprecated model name will return an error. To avoid interruptions, we encourage you to switch to a different model before then: We recommend gpt-oss-120b or llama-3.3-70b for most use cases For other use cases, consider qwen-3-235b-a22b-instruct-2507 for  You can explore all available models here   Thanks for using this Preview model and let us know if you have any questions.   The Cerebras team   Cerebras Systems, 1237 E Arques Ave, Sunnyvale, CA 94085 Unsubscribe Manage preferences