---
title: "LLM Throughput & GPU Sizing Calculator"
method: POST
path: "/api/v1/tools/llm-throughput-calculator"
tags: ["ai"]
---

# LLM Throughput & GPU Sizing Calculator

`POST /api/v1/tools/llm-throughput-calculator`

## Request

- Base URL: `https://calcfleet.com`
- URL: `https://calcfleet.com/api/v1/tools/llm-throughput-calculator`
- Auth: none declared

Estimate how many GPUs your LLM needs: concurrent users and target tokens per second become cluster size, monthly cloud cost, and real utilization at load.

## Request body

- object
  - `concurrentUsers` integer, required
  - `targetTokensPerSecPerUser` number, required
  - `gpuId` 'h100-sxm-80gb' | 'a100-sxm-80gb' | 'a100-40gb' | 'l40s-48gb' | 'rtx-4090-24gb', required
  - `gpuHourlyUsd` number, required
  - `aggregateTokensPerSecPerGpu` number, required
  - `utilizationHeadroomPct` number, required

## Response `200`

Successful calculation result.

- object
  - `result` object, required: Structured calculation output (fields vary per calculator).

## Other responses

- `400`: Invalid input — the issues array contains Zod validation errors.
- `403`: Forbidden — an Authorization: Bearer cf_… key was supplied but is invalid.
- `404`: Unknown tool slug.

---

[API](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api.md) · [All operations](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api/llms.txt) · [OpenAPI document](https://skmtc.dev/calcfleet/apis/calcfleet-financial-calculators-api/revisions/cd9abd595bbe?raw)