API reference · Schema
RateLevelLimits
inference_rpmintegerrequiredInference requests per minute, per model
inference_tpmintegerrequiredInference tokens (prompt + completion) per minute, per model
batch_rpmintegerrequiredBatch requests per minute, per model
batch_tpmintegerrequiredBatch tokens per minute, per model
Example
{
"inference_rpm": 1,
"inference_tpm": 1,
"batch_rpm": 1,
"batch_tpm": 1
}