Monthly cost of Cerebras Inference and Cohere at three volumes and at your own
Volume
Cerebras Inference
Cohere
small1M input, 200K output
$0.50 / moGPT OSS 120B
$0.0675 / moCommand R7B
growing50M input, 10M output
$25 / moGPT OSS 120B
$3.375 / moCommand R7B
scale1B input, 200M output
$500 / moGPT OSS 120B
$67.50 / moCommand R7B
your volumeset above
$25 / moGPT OSS 120B
$3.375 / moCommand R7B
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.