---
title: "Self-hosting LLM vs API cost calculator: GPU break-even"
description: "Is self-hosting an LLM cheaper than an API? Enter GPU price, count, utilisation and measured throughput to get cost per 1M tokens and the break-even volume."
url: https://broadrouter.com/tools/self-hosting-vs-api-calculator/
lang: en
updated: 2026-11-16
publisher: BroadRouter (a BroadNet site); API by BroadNet Inference, https://inference.broadnet.ai
---

# Self-hosting vs API cost calculator

Updated 2026-11-16

**In short:** Self-hosted cost per 1M tokens = GPU price per hour × GPUs ÷ (measured tokens per second × 3,600 × utilisation ÷ 1,000,000). One H100 at RunPod's Community Cloud rate costs about USD 1,964 a month always on, so it must replace about 8,048 million tokens a month of DeepSeek V4.1 Flash to break even.

Free, no sign-up, runs in your browser: nothing you type is sent anywhere.

Your GPUs and your volumeGPU and list priceH100 SXM 80GB, RunPod Secure CloudH100 SXM 80GB, RunPod Community CloudH100 PCIe 80GB, RunPod Secure CloudH200 141GB, RunPod Secure CloudB200 180GB, RunPod Secure CloudA100 SXM 80GB, RunPod Secure CloudL40S 48GB, RunPod Secure CloudRTX 4090 24GB, RunPod Community CloudH100 SXM 80GB, Lambda On-demand, 8-GPU nodeH100 SXM 80GB, Lambda On-demand, 1 GPUB200 180GB, Lambda On-demand, 8-GPU nodeA100 80GB, Lambda On-demand, 8-GPU nodeGH200 96GB, Lambda On-demand, 1 GPUH100 80GB, AWS EC2 p5.48xlarge, us-east-1H200 141GB, AWS EC2 p5en.48xlarge, us-east-1L40S 48GB, AWS EC2 g6e.xlarge, us-east-1Custom pricePrice per GPU-hour, USDGPUs per serverMeasured throughput, tokens per second (whole server, all requests)

Example value, not a benchmark. Replace it with what you measured for your model, engine and prompts.

Utilisation, % of hoursEngineering and ops, USD a monthMonthly tokens, millionsOutput share, %Input read from cache (API), %

Your current API (optional)Maker's list price or your ownNoneCustom: type the prices belowAI21 Labs jamba-large (maker's API, checked 2026-11-15)AI21 Labs jamba-mini (maker's API, checked 2026-11-15)Alibaba Cloud qwen-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen-max (maker's API, checked 2026-11-14)Alibaba Cloud qwen-mt-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen-mt-lite (maker's API, checked 2026-11-14)Alibaba Cloud qwen-mt-plus (maker's API, checked 2026-11-14)Alibaba Cloud qwen-plus (maker's API, checked 2026-11-14)Alibaba Cloud qwen3-coder-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3-omni-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3-vl-plus (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-122b-a10b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-27b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-35b-a3b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-397b-a17b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-flash-2026-02-23 (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-omni-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-omni-plus (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-plus-2026-02-15 (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.5-plus-2026-04-20 (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.6-27b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.6-35b-a3b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.6-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.6-plus (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.7-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.7-max (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.7-plus (maker's API, promotional price, checked 2026-11-14)Alibaba Cloud qwen3.8-2.4t-a95b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.8-27b (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.8-flash (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.8-max (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.8-max-0902 (maker's API, checked 2026-11-14)Alibaba Cloud qwen3.8-omni-flash (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova 2 Lite (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova 2 Omni (Preview) (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova 2 Pro (Preview) (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova Lite (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova Micro (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova Premier (maker's API, checked 2026-11-14)Amazon (Bedrock) Amazon Nova Pro (maker's API, checked 2026-11-14)Anthropic Claude Fable 5 (maker's API, checked 2026-11-14)Anthropic Claude Fable 5.1 (maker's API, checked 2026-11-14)Anthropic Claude Fable 5.2 (maker's API, checked 2026-11-14)Anthropic Claude Haiku 4.5 (maker's API, checked 2026-11-14)Anthropic Claude Haiku 5.5 (maker's API, checked 2026-11-14)Anthropic Claude Mythos 5 (maker's API, checked 2026-11-14)Anthropic Claude Mythos 5.1 (maker's API, checked 2026-11-14)Anthropic Claude Mythos 5.2 (maker's API, checked 2026-11-14)Anthropic Claude Opus 4.5 (maker's API, checked 2026-11-14)Anthropic Claude Opus 4.6 (maker's API, checked 2026-11-14)Anthropic Claude Opus 4.7 (maker's API, checked 2026-11-14)Anthropic Claude Opus 4.8 (maker's API, checked 2026-11-14)Anthropic Claude Opus 5 (maker's API, checked 2026-11-14)Anthropic Claude Opus 5.5 (maker's API, checked 2026-11-14)Anthropic Claude Sonnet 4.5 (maker's API, checked 2026-11-14)Anthropic Claude Sonnet 4.6 (maker's API, checked 2026-11-14)Anthropic Claude Sonnet 5 (maker's API, checked 2026-11-14)Anthropic Claude Sonnet 5.5 (maker's API, checked 2026-11-14)Baidu ERNIE 5.1 (maker's API, checked 2026-11-15)Baidu ernie-5.5-flash-preview (maker's API, checked 2026-11-15)Baidu ernie-light-dt-1.0 (maker's API, checked 2026-11-15)Cohere c4ai-aya-expanse-32b (maker's API, checked 2026-11-14)Cohere c4ai-aya-expanse-8b (maker's API, checked 2026-11-14)Cohere command-r-plus-08-2024 (maker's API, checked 2026-11-14)Cohere command-r7b-12-2024 (maker's API, checked 2026-11-14)DeepSeek deepseek-v4-pro (maker's API, peak-hour price, checked 2026-11-14)Google Gemini API gemini-2.5-flash-lite (maker's API, checked 2026-11-14)Google Gemini API gemini-3-flash-preview (maker's API, checked 2026-11-14)Google Gemini API gemini-3.1-flash-lite (maker's API, checked 2026-11-14)Google Gemini API gemini-3.1-pro-preview (maker's API, checked 2026-11-14)Google Gemini API gemini-3.5-flash-lite (maker's API, checked 2026-11-14)Google Gemini API gemini-3.6-flash (maker's API, promotional price, checked 2026-11-14)Google Gemini API gemini-3.8-flash (maker's API, promotional price, checked 2026-11-14)Google Gemini API gemini-4-argon (maker's API, promotional price, checked 2026-11-14)Google Gemini API gemini-4-carbon (maker's API, promotional price, checked 2026-11-14)Google Gemini API gemini-4-hydrogen (maker's API, checked 2026-11-14)IBM watsonx.ai granite-4h-small (maker's API, checked 2026-11-15)IBM watsonx.ai granite-8b-code-instruct (maker's API, checked 2026-11-15)MiniMax MiniMax-M3 (maker's API, checked 2026-11-14)MiniMax MiniMax-M3.1-Flash (maker's API, checked 2026-11-14)Mistral AI codestral-2508 (maker's API, checked 2026-11-14)Mistral AI ministral-14b-2512 (maker's API, checked 2026-11-14)Mistral AI ministral-3b-2512 (maker's API, checked 2026-11-14)Mistral AI ministral-8b-2512 (maker's API, checked 2026-11-14)Mistral AI mistral-large-4 (maker's API, checked 2026-11-14)Mistral AI mistral-small-2603 (maker's API, checked 2026-11-14)Moonshot AI kimi-k3 (maker's API, checked 2026-11-14)Moonshot AI kimi-k3.1-pro (maker's API, checked 2026-11-14)OpenAI chat-latest (maker's API, checked 2026-11-14)OpenAI gpt-4.1 (maker's API, checked 2026-11-14)OpenAI gpt-4.1-mini (maker's API, checked 2026-11-14)OpenAI gpt-4o (maker's API, checked 2026-11-14)OpenAI gpt-4o-mini (maker's API, checked 2026-11-14)OpenAI gpt-5 (maker's API, checked 2026-11-14)OpenAI gpt-5-mini (maker's API, checked 2026-11-14)OpenAI gpt-5-nano (maker's API, checked 2026-11-14)OpenAI gpt-5-pro (maker's API, checked 2026-11-14)OpenAI gpt-5-search-api (maker's API, checked 2026-11-14)OpenAI gpt-5.1 (maker's API, checked 2026-11-14)OpenAI gpt-5.2 (maker's API, checked 2026-11-14)OpenAI gpt-5.2-pro (maker's API, checked 2026-11-14)OpenAI gpt-5.3-codex (maker's API, checked 2026-11-14)OpenAI gpt-5.4 (maker's API, checked 2026-11-14)OpenAI gpt-5.4-mini (maker's API, checked 2026-11-14)OpenAI gpt-5.4-nano (maker's API, checked 2026-11-14)OpenAI gpt-5.4-pro (maker's API, checked 2026-11-14)OpenAI gpt-5.5 (maker's API, checked 2026-11-14)OpenAI gpt-5.5-cyber-preview (maker's API, checked 2026-11-14)OpenAI gpt-5.5-pro (maker's API, checked 2026-11-14)OpenAI gpt-5.6-cyber (maker's API, checked 2026-11-14)OpenAI gpt-5.6-luna (maker's API, checked 2026-11-14)OpenAI gpt-5.6-sol (maker's API, promotional price, checked 2026-11-14)OpenAI gpt-5.6-terra (maker's API, checked 2026-11-14)OpenAI gpt-6-astra (maker's API, checked 2026-11-14)OpenAI gpt-6-astra-law (maker's API, promotional price, checked 2026-11-14)OpenAI gpt-6-cyber (maker's API, checked 2026-11-14)OpenAI gpt-6-luna (maker's API, checked 2026-11-14)OpenAI gpt-6-rosalind (maker's API, checked 2026-11-14)OpenAI gpt-6-sol (maker's API, checked 2026-11-14)OpenAI gpt-6.1-sol (maker's API, checked 2026-11-14)OpenAI gpt-6.1-terra (maker's API, checked 2026-11-14)OpenAI gpt-rosalind-discovery (maker's API, checked 2026-11-14)OpenAI gpt-rosalind-research (maker's API, checked 2026-11-14)OpenAI o3 (maker's API, checked 2026-11-14)OpenAI o3-pro (maker's API, checked 2026-11-14)Perplexity perplexity/sonar (maker's API, checked 2026-11-15)xAI grok-4.20-0309-non-reasoning (maker's API, checked 2026-11-14)xAI grok-4.20-0309-reasoning (maker's API, checked 2026-11-14)xAI grok-4.20-multi-agent-0309 (maker's API, checked 2026-11-14)xAI grok-4.3 (maker's API, checked 2026-11-14)xAI grok-4.5 (maker's API, checked 2026-11-14)xAI grok-4.6 (maker's API, checked 2026-11-14)xAI grok-4.7 (maker's API, checked 2026-11-14)xAI grok-build-0.1 (maker's API, checked 2026-11-14)Z.ai GLM-4-32B-0414-128K (maker's API, checked 2026-11-14)Z.ai GLM-4.5 (maker's API, checked 2026-11-14)Z.ai GLM-4.5-Air (maker's API, checked 2026-11-14)Z.ai GLM-4.5-AirX (maker's API, checked 2026-11-14)Z.ai GLM-4.5-X (maker's API, checked 2026-11-14)Z.ai GLM-4.5V (maker's API, checked 2026-11-14)Z.ai GLM-4.6 (maker's API, checked 2026-11-14)Z.ai GLM-4.6V (maker's API, checked 2026-11-14)Z.ai GLM-4.6V-FlashX (maker's API, checked 2026-11-14)Z.ai GLM-4.7 (maker's API, checked 2026-11-14)Z.ai GLM-4.7-FlashX (maker's API, checked 2026-11-14)Z.ai GLM-5 (maker's API, checked 2026-11-14)Z.ai GLM-5.1 (maker's API, checked 2026-11-14)Z.ai GLM-5.2 (maker's API, checked 2026-11-14)Z.ai GLM-5.3 (maker's API, checked 2026-11-14)Z.ai GLM-5.3-Flash (maker's API, checked 2026-11-14)Z.ai GLM-5.3-FlashX (maker's API, checked 2026-11-14)Z.ai GLM-5.3-FlashX-Legal (maker's API, checked 2026-11-14)NameInput, USD per 1MOutput, USD per 1MCached input, USD per 1M (blank = input price)

Self-hosted cost against your API and BroadNet API prices and plans
| Option | Per 1M tokens | Per month at your volume | Self-hosting breaks even at |
| --- | --- | --- | --- |

[See BroadNet prices](https://inference.broadnet.ai/pricing?utm_source=broadrouter&utm_medium=referral&utm_campaign=tools-self-hosting-vs-api-calculator&utm_content=tool) ·

Estimates, before tax. GPU presets are on-demand list prices checked 2026-11-14; reserved, spot and committed-use prices are lower. BroadNet prices synced 2026-11-14. "Your current API" presets are each maker's standard list price on its own API (lowest prompt-size tier), read from the maker's pricing page on the date shown; batch, off-peak and volume discounts are not applied, so type your real price if it differs. The comparison assumes the self-hosted model is good enough for your task; a model you host is not the same model as the API rows, so compare quality first. Flat plans run DeepSeek V4.1 Flash only, one request at a time per session; the hourly key runs BroadNet Gemma 4 VL 26B.

[Report a wrong price or number](mailto:info@broadnet.ai?subject=Wrong%20price%20or%20number%20on%20Self-hosting%20vs%20API%20cost%20calculator&body=Page%3A%20https%3A%2F%2Fbroadrouter.com%2Ftools%2Fself-hosting-vs-api-calculator%2F%0A%0AWhat%20looks%20wrong%20(model%2C%20figure%20shown%2C%20correct%20figure%20and%20a%20source%20link%20if%20you%20have%20one)%3A%0A) (email to info@broadnet.ai, with this page's link and your inputs filled in).

## How it works

1.  Choose a GPU preset (official on-demand list prices from RunPod, Lambda and AWS, dated) or type your own hourly price, then the number of GPUs one model server needs.
2.  Enter the throughput you measured for that server, in tokens per second across all concurrent requests, and the share of the month it runs at that rate (utilisation).
3.  Enter your monthly volume in millions of tokens, the share that is output, the share of input served from cache, and any monthly engineering and ops cost.
4.  Optionally enter the API you use now: pick a maker's list price or type your own input, cached-input and output prices per 1M tokens. It gets its own row and break-even.
5.  Read the table: self-hosted cost per 1M tokens and per month against your API, every BroadNet per-token price and flat plan, with the break-even volume. Copy the link or download CSV.

## The formula

```
server cost per hour     = GPU price per hour × GPUs
tokens per month (cap)   = tokens per second × 3,600 × 730 × utilisation
self-hosted per 1M       = server cost per hour / (tokens per second × 3,600 × utilisation / 1,000,000)
servers needed           = ceil(monthly tokens / tokens per month cap)
self-hosted per month    = servers × server cost per hour × 730 + ops
API per month            = input × (1 − cache) × input price + input × cache × cached price
                         + output × output price          (per 1M tokens)
break-even volume        = (server cost per hour × 730 + ops) / API price per 1M
break-even utilisation   = (server cost per hour × 730 + ops)
                           / (tokens per second × 3,600 × 730 / 1,000,000 × API price per 1M)
```

A month here is 730 hours (8,760 ÷ 12), and the servers are rented always-on, as most teams run a production model. Utilisation is the share of those hours the server spends at the throughput you measured; idle nights, traffic peaks you must keep headroom for and a standby node all lower it. If break-even volume is larger than one server's monthly capacity, self-hosting cannot match that API price at your throughput. See [GPU-hour](https://broadrouter.com/glossary/gpu-hour/), [tokens per second](https://broadrouter.com/glossary/tokens-per-second/) and [quantization](https://broadrouter.com/glossary/quantization/) in the glossary.

## GPU list prices

On-demand prices per GPU-hour from each provider's official page, checked 2026-11-14. A month is 730 hours.

| GPU | Provider and tier | Per GPU-hour | Per month, always on | Notes and source |
| --- | --- | --- | --- | --- |
| H100 SXM 80GB | RunPod Secure Cloud | USD 4.39 | about USD 3,205 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| H100 SXM 80GB | RunPod Community Cloud | USD 2.69 | about USD 1,964 | "From" price; varies by host. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| H100 PCIe 80GB | RunPod Secure Cloud | USD 2.89 | about USD 2,110 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| H200 141GB | RunPod Secure Cloud | USD 5.29 | about USD 3,862 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| B200 180GB | RunPod Secure Cloud | USD 7.99 | about USD 5,833 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| A100 SXM 80GB | RunPod Secure Cloud | USD 2.19 | about USD 1,599 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| L40S 48GB | RunPod Secure Cloud | USD 1.09 | about USD 796 | Billed per second. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| RTX 4090 24GB | RunPod Community Cloud | USD 0.34 | about USD 248 | "From" price; varies by host. [Pricing](https://www.runpod.io/pricing), checked 2026-11-14. |
| H100 SXM 80GB | Lambda On-demand, 8-GPU node | USD 4.59 | about USD 3,351 | Lambda says its listed prices take effect 2026-11-16 at 00:00 UTC; plus sales tax. [Pricing](https://lambda.ai/pricing), checked 2026-11-14. |
| H100 SXM 80GB | Lambda On-demand, 1 GPU | USD 4.89 | about USD 3,570 | Lambda says its listed prices take effect 2026-11-16 at 00:00 UTC; plus sales tax. [Pricing](https://lambda.ai/pricing), checked 2026-11-14. |
| B200 180GB | Lambda On-demand, 8-GPU node | USD 7.69 | about USD 5,614 | Lambda says its listed prices take effect 2026-11-16 at 00:00 UTC; plus sales tax. [Pricing](https://lambda.ai/pricing), checked 2026-11-14. |
| A100 80GB | Lambda On-demand, 8-GPU node | USD 3.19 | about USD 2,329 | Lambda says its listed prices take effect 2026-11-16 at 00:00 UTC; plus sales tax. [Pricing](https://lambda.ai/pricing), checked 2026-11-14. |
| GH200 96GB | Lambda On-demand, 1 GPU | USD 2.59 | about USD 1,891 | Lambda says its listed prices take effect 2026-11-16 at 00:00 UTC; plus sales tax. [Pricing](https://lambda.ai/pricing), checked 2026-11-14. |
| H100 80GB | AWS EC2 p5.48xlarge, us-east-1 | USD 6.88 | about USD 5,022 | p5.48xlarge, 8 GPUs, USD 55.04 an hour for the instance in us-east-1 (Linux, on-demand), divided by 8. Includes the CPU, memory and storage bundled with the instance. [Pricing](https://aws.amazon.com/ec2/pricing/on-demand/), checked 2026-11-14. |
| H200 141GB | AWS EC2 p5en.48xlarge, us-east-1 | USD 7.91 | about USD 5,776 | p5en.48xlarge, 8 GPUs, USD 63.296 an hour for the instance in us-east-1 (Linux, on-demand), divided by 8. Includes the CPU, memory and storage bundled with the instance. [Pricing](https://aws.amazon.com/ec2/pricing/on-demand/), checked 2026-11-14. |
| L40S 48GB | AWS EC2 g6e.xlarge, us-east-1 | USD 1.86 | about USD 1,359 | g6e.xlarge, 1 GPU, USD 1.861 an hour for the instance in us-east-1 (Linux, on-demand), divided by 1. Includes the CPU, memory and storage bundled with the instance. [Pricing](https://aws.amazon.com/ec2/pricing/on-demand/), checked 2026-11-14. |

The calculator ships no throughput numbers on purpose. Tokens per second for the same GPU can differ several times over between a small quantized model with big batches and a large model serving long prompts one at a time, so a borrowed benchmark would decide the answer for you. The [self-hosting vs API post](https://broadrouter.com/blog/self-hosting-llm-vs-api-cost/) walks through how to measure it.

## Worked example

One H100 SXM on RunPod Community Cloud at USD 2.69 an hour costs about USD 1,964 a month. Suppose you measured 1,500 tokens per second (an assumption for this example) and the server is busy half the time: that is 1,971 million tokens a month at USD 1.00 per 1M tokens. With 80% input and 20% output, DeepSeek V4.1 Flash costs USD 0.24 per 1M tokens and BroadNet Gemma 4 VL 26B USD 0.12, so this server needs about 8,048 million and 15,836 million tokens a month to break even. Its capacity is 1,971 million, so at these numbers the API is cheaper, and a Full Moon session at $60 a month (up to about 263 million output tokens at 100 tokens per second) costs less again for a single agent that runs one request at a time.

## When self-hosting is still the right call

-   Data must stay inside your network, and an API with [zero data retention](https://broadrouter.com/zero-data-retention/) does not meet your rules.
-   You serve your own fine-tune or a model no API offers.
-   You keep GPUs saturated around the clock with batch work.
-   You need guaranteed capacity beyond an API's rate limits; the [rate limit calculator](https://broadrouter.com/tools/llm-rate-limit-calculator/) shows what a key allows.

To price the API side in more detail, with cache hits and reasoning tokens, use the [LLM API cost calculator](https://broadrouter.com/tools/llm-api-cost-calculator/); to compare a flat plan with per-token billing, the [flat-rate vs per-token calculator](https://broadrouter.com/tools/flat-rate-vs-per-token-calculator/). The $5 starting credit is enough to measure your own prompts on BroadNet first.

## Questions

### Is it cheaper to self-host an LLM than to use an API?

Only at high, steady volume. A rented GPU bills every hour whether it is busy or idle; an API bills only the tokens you use. One H100 SXM at RunPod's Community Cloud rate (USD 2.69 an hour, checked 2026-11-14) costs about USD 1,964 a month left running, so it has to replace about 8,048 million tokens a month of DeepSeek V4.1 Flash at its blended price to break even, before engineering time.

### How do you calculate the cost per token of a self-hosted LLM?

Divide what the GPUs cost per hour by the tokens they produce per hour: cost per 1M tokens = GPU price per hour × number of GPUs ÷ (tokens per second × 3,600 × utilisation ÷ 1,000,000). Utilisation is the share of hours the server really runs at that speed. Add engineering and on-call time as a monthly cost on top.

### How many tokens per second does an H100 generate?

There is no single number. Throughput depends on the model size, quantization, serving engine (such as vLLM or SGLang), batch size, prompt and answer lengths, and concurrency. Run your own prompts at your real concurrency and record total tokens per second across all requests. That measured figure is the one this calculator needs; vendor peak figures assume ideal batching.

### How much does it cost to rent an H100 per hour?

On 2026-11-14: RunPod listed H100 SXM at USD 4.39 an hour on Secure Cloud and from USD 2.69 on Community Cloud; Lambda listed USD 4.59 to 4.89 per GPU-hour on demand, for prices taking effect 2026-11-16; AWS's p5.48xlarge (8 × H100) was USD 55.04 an hour in us-east-1, about USD 6.88 per GPU. The presets carry these prices; check the pages before you commit.

### What utilisation do I need to break even with an API?

Solve the cost formula for utilisation: break-even utilisation = GPU cost per hour ÷ (tokens per second × 3,600 ÷ 1,000,000 × API price per 1M tokens). Add your monthly engineering cost divided by 730 to the GPU cost per hour if you count it. If the answer is above 100%, the server cannot beat that API price at your throughput, however busy it is. The calculator shows this for each BroadNet model and for the API you use now, if you enter its prices.

### What costs do people forget when they self-host?

Engineering to set up serving and autoscaling, upgrades and model refreshes, on-call, a second node for redundancy (which halves utilisation), idle headroom for peaks, and evaluation before each model switch. Enter them as a monthly cost in the "Engineering and ops" field. [Self-hosting vs API: the full cost list](https://broadrouter.com/blog/self-hosting-llm-vs-api-cost/).

## Go deeper

-   [Self-hosting an LLM vs an API: the real cost and break-even](https://broadrouter.com/blog/self-hosting-llm-vs-api-cost/)
-   [Open-weight vs closed models](https://broadrouter.com/blog/open-weight-vs-closed-models/)
-   [LLM latency, TTFT and throughput](https://broadrouter.com/blog/llm-latency-ttft-throughput/)
-   [Glossary: GPU-hour](https://broadrouter.com/glossary/gpu-hour/)
-   [Glossary: throughput](https://broadrouter.com/glossary/throughput/)

## More free tools

-   [**LLM API cost calculator**Price a workload on every model at once, with cache hits, reasoning and a flat-plan check.](https://broadrouter.com/tools/llm-api-cost-calculator/)
-   [**Speech-to-text cost calculator**Hours, calls or voice notes to a monthly transcription bill, against your current provider.](https://broadrouter.com/tools/speech-to-text-cost-calculator/)
-   [**LLM token counter**Exact token counts with each model's real tokenizer, with a token view and cost.](https://broadrouter.com/tools/token-counter/)
-   [**Arabic token counter**Arabic vs English token counts per tokenizer: the "Arabic tax" in tokens and money.](https://broadrouter.com/tools/arabic-token-counter/)
-   [**Tokens to words converter**Tokens ↔ words ↔ characters ↔ pages, by language and content type.](https://broadrouter.com/tools/tokens-to-words/)
-   [**Context window calculator**Will it fit? Window used per model, room left for output, cost to send.](https://broadrouter.com/tools/context-window-calculator/)
-   [**Flat-rate vs per-token LLM cost calculator**Break-even between an unlimited plan and paying per token, per agent.](https://broadrouter.com/tools/flat-rate-vs-per-token-calculator/)
-   [**Prompt caching savings calculator**Bill with and without caching, by prefix share and hit rate.](https://broadrouter.com/tools/prompt-caching-calculator/)
-   [**Image token calculator**Tokens and cost per image under each model's documented rule. Drop an image; nothing is uploaded.](https://broadrouter.com/tools/image-token-calculator/)
-   [**Embedding cost calculator**Index, update and query costs for a corpus at OpenAI, Google, Voyage, Mistral and Jina list prices.](https://broadrouter.com/tools/embedding-cost-calculator/)
-   [**LLM rate limit and concurrency calculator**Which limit binds first: RPM, TPM or concurrency, with Little's law.](https://broadrouter.com/tools/llm-rate-limit-calculator/)
-   [**JSON schema generator for LLM structured output**Sample JSON to strict schema, Pydantic, Zod and a ready request.](https://broadrouter.com/tools/json-schema-generator/)
-   [**OpenAI-compatible API request builder**One request, copied as curl, Python, Node or the OpenAI SDKs.](https://broadrouter.com/tools/api-request-builder/)
-   [**Audio file splitter for speech-to-text limits**Chunk count, overlap and copy-ready ffmpeg commands to fit a transcription file-size limit.](https://broadrouter.com/tools/audio-splitter-ffmpeg/)
-   [**Agent run cost estimator**Context growth per step, total tokens and cost of one agent run, with a DeepSeek session comparison.](https://broadrouter.com/tools/agent-run-cost-estimator/)
-   [**OpenAI to BroadNet migration helper**Paste OpenAI SDK code; get base URL, key and model edits, a diff and the checks that remain.](https://broadrouter.com/tools/openai-to-broadnet-migration/)
-   [**Arabic text normalizer**Tashkeel, tatweel, alef, ya, ta marbuta, digits and invisible characters, with a matching Python function.](https://broadrouter.com/tools/arabic-text-normalizer/)
-   [**RAG chunking calculator**Chunks, embedding tokens, input per query, context check and monthly LLM cost for a RAG pipeline.](https://broadrouter.com/tools/rag-chunking-calculator/)
-   [**max\_tokens calculator for reasoning models**Answer length + reasoning budget + margin = a max\_tokens that does not cut the answer off.](https://broadrouter.com/tools/reasoning-token-budget/)
-   [**LLM batch job planner**Run time, binding limit, cost per model and the flat sessions needed to finish a big job by a deadline.](https://broadrouter.com/tools/llm-batch-job-planner/)
-   [**LLM JSON output validator**Parse errors by line and column, safe repairs, cut-off detection and JSON Schema checks for model output.](https://broadrouter.com/tools/llm-json-output-validator/)
-   [**Prompt token diff**Two prompt versions side by side: changed lines, exact token delta and the monthly cost difference.](https://broadrouter.com/tools/prompt-token-diff/)

Try it on your real workload. New accounts start with $5 of credit for Gemma and transcription. DeepSeek, GLM and Qwen3.8 need a top-up.

[Get started](https://inference.broadnet.ai/account/?utm_source=broadrouter&utm_medium=referral&utm_campaign=tools-self-hosting-vs-api-calculator&utm_content=page-cta) ·

**Sources**

-   [BroadNet Inference machine-readable prices (pricing.json)](https://inference.broadnet.ai/pricing.json?utm_source=broadrouter&utm_medium=referral&utm_campaign=tools-self-hosting-vs-api-calculator&utm_content=sources)
-   [RunPod GPU pricing (Secure and Community Cloud), checked 2026-11-14](https://www.runpod.io/pricing)
-   [Lambda on-demand GPU pricing, checked 2026-11-14](https://lambda.ai/pricing)
-   [AWS EC2 on-demand price list, us-east-1 Linux (published 2026-11-14), checked 2026-11-14](https://b0.p.awsstatic.com/pricing/2.0/meteredUnitMaps/ec2/USD/current/ec2-ondemand-without-sec-sel/US%20East%20(N.%20Virginia)/Linux/index.json)
-   [AWS EC2 P5 instance specs (GPUs per instance), checked 2026-11-14](https://aws.amazon.com/ec2/instance-types/p5/)
-   [BroadNet Inference plans and typical speed](https://inference.broadnet.ai/plans?utm_source=broadrouter&utm_medium=referral&utm_campaign=tools-self-hosting-vs-api-calculator&utm_content=sources)
-   [BroadNet Inference API reference, limits](https://inference.broadnet.ai/docs?utm_source=broadrouter&utm_medium=referral&utm_campaign=tools-self-hosting-vs-api-calculator&utm_content=sources#limits)
