Cost simulator
Estimate hosted and self-hosted cost for a model and token counts.
1. Estimate
Enter a model ID and your expected monthly token volume. The simulator returns projected hosted-API cost and self-hosted GPU cost per cloud provider.
Open Advanced and navigate to Simulator (/advanced/simulator). Pick a model from the dropdown, then set prompt tokens, completion tokens, your expected monthly volume, and a self-hosted utilization percentage. Results update live as you change any field, there is no separate submit step. The results show projected hosted-API cost and self-hosted cost for AWS, Azure, and GCP, each scaled to your monthly volume.
Not available via the CLI. Use the app or MCP.
Call simulate_cost with a model ID and token counts:
{
"model": "gpt-4o-mini",
"prompt_tokens": 500,
"completion_tokens": 200
}The response includes projected hosted-API cost and self-hosted cost per cloud (AWS, Azure, GCP) for that token count. To estimate a monthly total, multiply the per-call figures by your expected call volume yourself, the tool does not take a volume argument.
Last verified .