AI token cost
calculator
Calculate and compare the real cost of calling AI models. Enter tokens or paste a prompt — get instant estimates.
Calculate cost
Select a model, enter token counts,
and hit Calculate.
Pipeline composition
Chain models together — output of each step feeds the next.
The prompt / context that kicks off the pipeline.
$2.5 / $10 per 1M
→ feeds as input to the next step
$2.5 / $10 per 1M
→ feeds as input to the next step
Configure your pipeline steps and hit calculate to see the total cost breakdown.
Compare models
Select 2 or more models to compare side-by-side.
Select models
Self-hosted cost
Pick a model, GPU and cluster config — costs calculated from real benchmarks
Llama
Mistral
Mixtral
Qwen
Phi
Gemma
DeepSeek
FP16 (full precision)
Number of GPUs
Utilization %
Leave at 0 to use the benchmark value above. Set your own if you've profiled the actual model on your hardware.
Input tokens
Output tokens
Self-hosted inference has a unified cost — input and output share the same throughput budget.
Cost per million tokens
$0.4336
Effective throughput: 2,242 tok/s
$2555/mo (730h)
At scale