Monthly cost of Cerebras Inference and Groq at three volumes and at your own
Volume
Cerebras Inference
Groq
small1M input, 200K output
$0.50 / moGPT OSS 120B
$0.036 / moLlama Prompt Guard 2 22M
growing50M input, 10M output
$25 / moGPT OSS 120B
$1.80 / moLlama Prompt Guard 2 22M
scale1B input, 200M output
$500 / moGPT OSS 120B
$36 / moLlama Prompt Guard 2 22M
your volumeset above
$25 / moGPT OSS 120B
$1.80 / moLlama Prompt Guard 2 22M
Each cell is the cheapest feasible plan, or the chosen model, at that volume, from the shared Overage cost function. "Cheapest model" only considers models with both an input and an output price listed. Volumes are example scenarios you can edit.