Serverless and AWS cost estimators for AI workloads.
Estimate combined AWS Lambda and LLM cost per invocation.
Estimate AWS Lambda compute and request cost.
Estimate AWS CloudFront data transfer and request cost.
Estimate DynamoDB on-demand read, write and storage cost.
Estimate Amazon S3 storage, request and transfer cost.
Estimate OpenSearch Serverless compute and storage cost.
Find the volume where self-hosting beats API pricing.
See response time and throughput at a given tokens/sec.
Find the tokens/sec needed to hit a latency target.
Size concurrency and instances for a target request rate.
Check if your traffic fits provider TPM and RPM limits.
Estimate the VRAM needed to run a model locally.
Estimate tokens/sec for a model on your GPU.
Estimate monthly cost of renting cloud GPUs.
Compare model VRAM across fp32, fp16, int8 and int4.
Find how many GPUs you need for a target tokens/sec.
Estimate GPU-hour cost and wall-clock time for a training run.