> ## 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 Cloud API: Get Your First Token in Minutes

> Sign up for Boole AI, grab an API key, and make your first cloud API call in minutes — includes 1 million free tokens, no credit card required.

This guide gets you from zero to a working API call in a few minutes. You'll create a free Boole account — no credit card required — receive \$20 in credits (enough for roughly 1 million tokens), generate an API key, and stream a response from Llama 3.3 70B. Because Boole is fully OpenAI-compatible, you can use the OpenAI SDK in any language you already know.

## Steps

<Steps>
  <Step title="Create your account">
    Go to [booleinference.com/signup](https://booleinference.com/signup) and create a free account. No credit card is required at signup — you receive **\$20 in free credits** automatically, good for roughly 1 million input tokens on Llama 3.3 70B.
  </Step>

  <Step title="Generate an API key">
    After signing in, navigate to **Settings → API Keys** in the dashboard and click **Create new key**. Give it a descriptive name, then copy the key — it is only shown once.

    <Warning>
      Store your API key securely. Never commit it to source control or expose it in client-side code. If a key is compromised, revoke it immediately from the dashboard and generate a replacement.
    </Warning>
  </Step>

  <Step title="Set the environment variable">
    Export your key as an environment variable so your code can read it without hard-coding the value.

    ```bash theme={null}
    export BOOLE_API_KEY="your-api-key-here"
    ```

    Add this line to your shell profile (`.bashrc`, `.zshrc`, etc.) to persist it across sessions.
  </Step>

  <Step title="Make your first API call">
    Use the code sample below for your preferred language or tool. All three examples stream the response token by token.

    <CodeGroup>
      ```python app.py theme={null}
      from openai import OpenAI
      import os

      client = OpenAI(
          base_url="https://api.boole.dev/v1",
          api_key=os.environ["BOOLE_API_KEY"],
      )

      response = client.chat.completions.create(
          model="llama-3.3-70b-instruct",
          messages=[{"role": "user", "content": "Summarise this ticket."}],
          stream=True,
      )

      for chunk in response:
          print(chunk.choices[0].delta.content or "", end="", flush=True)
      ```

      ```javascript index.mjs theme={null}
      import OpenAI from "openai";

      const client = new OpenAI({
        baseURL: "https://api.boole.dev/v1",
        apiKey: process.env.BOOLE_API_KEY,
      });

      const response = await client.chat.completions.create({
        model: "llama-3.3-70b-instruct",
        messages: [{ role: "user", content: "Summarise this ticket." }],
        stream: true,
      });

      for await (const chunk of response) {
        process.stdout.write(chunk.choices[0]?.delta?.content || "");
      }
      ```

      ```bash curl theme={null}
      curl https://api.boole.dev/v1/chat/completions \
        -H "Authorization: Bearer $BOOLE_API_KEY" \
        -H "Content-Type: application/json" \
        -d '{
          "model": "llama-3.3-70b-instruct",
          "messages": [{"role": "user", "content": "Summarise this ticket."}],
          "stream": true
        }'
      ```
    </CodeGroup>

    <Info>
      Expect your **first token in approximately 62 ms** for Llama 3.3 70B. The default rate limit is 60 requests/sec per API key — contact [support@boole.ai](mailto:support@boole.ai) to request an increase.
    </Info>
  </Step>
</Steps>

<Tip>
  The same code runs against your local Boole server — just swap `base_url` from `https://api.boole.dev/v1` to `http://localhost:8000/v1`. This makes it trivial to develop locally and deploy to the cloud without changing any other logic.
</Tip>

## Pricing at a Glance

All cloud API usage is billed per token (input and output separately) or per minute for audio models. Prices listed below decrease automatically as the nightly compiler produces faster, more efficient model variants — you never need to do anything to benefit.

| Model                  | Input         | Output        |
| ---------------------- | ------------- | ------------- |
| Llama 3.3 70B Instruct | \$0.09 / MTok | \$0.14 / MTok |
| Qwen 2.5 72B           | \$0.11 / MTok | \$0.16 / MTok |
| Mixtral 8×22B          | \$0.13 / MTok | \$0.19 / MTok |
| DeepSeek V3            | \$0.08 / MTok | \$0.12 / MTok |
| Whisper Large v3       | \$0.02 / min  | —             |

<Note>
  MTok = 1 million tokens. See the full [pricing page](/concepts/pricing) for all 42 models and volume discount tiers.
</Note>

## Next Steps

<CardGroup cols={3}>
  <Card title="API Keys" icon="key" href="/account/api-keys">
    Rotate, scope, and revoke API keys from your dashboard.
  </Card>

  <Card title="Available Models" icon="layer-group" href="/concepts/models">
    Browse all 42 models with context lengths, capabilities, and pricing.
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/overview">
    Complete reference for every endpoint, request parameter, and response field.
  </Card>
</CardGroup>