> ## Documentation Index
> Fetch the complete documentation index at: https://docs.booleinference.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Boole AI Pricing: Cloud API Rates and Local Deployment

> Local deployment is free after hardware costs. Cloud API rates start at $0.08/MTok and only decrease. New accounts get $20 free credits, no card needed.

Boole AI has two cost models. Local deployment is free after hardware costs — you pay for your GPU once and run unlimited tokens with no usage-based billing. The cloud API is billed per token at rates that only decrease as the nightly compiler finds new efficiencies; prices never increase as a result of compiler changes.

## Local Deployment

Running the local binary has no per-token cost. Once you download the binary, you own it — no phone-home, no metering, no internet connection required.

* **Zero per-token cost.** Every token you generate is free.
* **No usage-based billing.** There is no meter running in the background.
* **Pay for your GPU once; run unlimited tokens.** A single A10 delivers 312 tokens/sec on Llama 3.3 70B.
* **No internet required after download.** The binary has weights embedded and operates fully offline.

See the [local quickstart](/quickstart-local) for instructions on downloading and running the binary.

## Cloud API Pricing

The table below shows current cloud API rates alongside the lowest price available for the same model elsewhere.

| Model                  | Input       | Output      | Cheapest Elsewhere |
| ---------------------- | ----------- | ----------- | ------------------ |
| Llama 3.3 70B Instruct | \$0.09/MTok | \$0.14/MTok | \$0.58/MTok        |
| Qwen 2.5 72B Instruct  | \$0.11/MTok | \$0.16/MTok | \$0.62/MTok        |
| Mixtral 8x22B          | \$0.13/MTok | \$0.19/MTok | \$0.65/MTok        |
| DeepSeek V3            | \$0.08/MTok | \$0.12/MTok | \$0.41/MTok        |
| Whisper Large v3       | \$0.02/min  | —           | \$0.11/hr          |

<Note>
  Prices decrease as the compiler finds new efficiencies and those savings are passed on to you directly. Prices never increase without at least 30 days of advance notice.
</Note>

## Free Credits

Every new account receives **\$20 in credits** — approximately 1 million tokens on Llama 3.3 70B Instruct. No credit card is required to sign up and start using the API. Credits are applied automatically to your first requests.

## Billing

Cloud API usage is billed per token for text models and per minute of audio for Whisper. You can monitor your usage and remaining balance in the [billing dashboard](/account/billing) at any time.

A few things to keep in mind:

* Usage is tallied in real time and visible in your dashboard immediately.
* Accounts with an outstanding balance may be suspended until payment is made.
* You can set a monthly spend cap in the dashboard to avoid unexpected charges.

## Cost Comparison

For the same underlying models, the Boole cloud API is typically around **one-tenth the cost** of the next cheapest alternative. This gap is a direct result of the nightly compiler: as efficiency improves, the cost to serve each token falls, and those savings are passed on rather than absorbed as margin.

<Tip>
  If you process high volumes, local deployment pays for itself within the first two weeks of use compared to cloud alternatives at standard market rates.
</Tip>

Manage your payment methods, invoices, and spend caps on the [billing page](/account/billing).