# Boole AI

## Docs

- [Boole AI: Local-First High-Throughput LLM Inference](https://docs.booleinference.com/introduction.md): Boole AI delivers high-throughput LLM inference via a local binary or cloud API — OpenAI-compatible, zero telemetry, and optimized nightly.
- [Boole AI Local Quickstart: GPU Inference in Minutes](https://docs.booleinference.com/quickstart-local.md): Download the Boole binary, start serving a model on your NVIDIA GPU, and get your first tokens in under 4 minutes — no Python or dependencies needed.
- [Boole AI Cloud API: Get Your First Token in Minutes](https://docs.booleinference.com/quickstart-api.md): 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.
- [How the Boole AI Inference Engine Works Under the Hood](https://docs.booleinference.com/concepts/inference-engine.md): Boole's nightly compiler runs 2,057 iterations of kernel fusion, quantization, and KV cache paging to maximize throughput while quality never regresses.
- [Boole AI Supported Models: Slugs, Pricing, and Performance](https://docs.booleinference.com/concepts/models.md): Boole AI supports 42 compiler-optimized models for local and cloud use. Learn how to reference each model by slug in API calls and CLI commands.
- [Boole AI Pricing: Cloud API Rates and Local Deployment](https://docs.booleinference.com/concepts/pricing.md): 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.
- [Deploy the Boole AI Binary — No Python, No Dependencies](https://docs.booleinference.com/deployment/local-binary.md): Download and run the Boole AI binary on your GPU — a single executable with no Python runtime, no dependency setup, and a cold start under 400 ms.
- [Run Boole AI with Docker and NVIDIA GPU Passthrough](https://docs.booleinference.com/deployment/docker.md): Pull the official Boole AI Docker image, pass through your NVIDIA GPU with a single flag, and start serving LLM inference in one containerized command.
- [Scale Boole AI on Kubernetes: GPU Pods, PVCs, and Probes](https://docs.booleinference.com/deployment/kubernetes.md): Deploy Boole AI on Kubernetes: schedule GPU pods, persist model weights with a PVC, and add liveness and readiness probes for production use.
- [Boole AI Cloud API: OpenAI-Compatible Managed Inference](https://docs.booleinference.com/deployment/cloud-api.md): Connect to the Boole AI cloud API — OpenAI-compatible endpoints, zero-retention policy, SOC 2 Type II certified, and $20 free credits to start.
- [OpenAI API Compatibility — Boole AI Integration Guide](https://docs.booleinference.com/integration/openai-compatibility.md): Boole AI implements the full OpenAI API spec. Swap your base URL and API key and every existing SDK, tool, and integration works instantly.
- [Python Integration Guide for Boole AI — OpenAI SDK](https://docs.booleinference.com/integration/python.md): Install the openai Python package and make chat, streaming, async, and tool-call requests against Boole AI's high-throughput inference API.
- [Node.js Integration Guide for Boole AI — OpenAI SDK](https://docs.booleinference.com/integration/nodejs.md): Install the openai npm package and make chat, streaming, and tool-call requests to Boole AI from any Node.js or TypeScript application.
- [Call the Boole AI REST API with cURL — HTTP Examples](https://docs.booleinference.com/integration/curl.md): Make direct HTTP requests to the Boole AI API using cURL — ideal for testing endpoints, debugging responses, and writing shell scripts.
- [Managing Boole AI API Keys: Create, Rotate, Revoke](https://docs.booleinference.com/account/api-keys.md): Create, rotate, and revoke API keys to authenticate requests to the Boole AI cloud API. Manage multiple keys per environment or team.
- [Boole AI Billing: Free Credits, Pricing, and Invoices](https://docs.booleinference.com/account/billing.md): Understand pay-per-use billing, claim your $20 in free signup credits, add a payment method, and download invoices for the Boole AI cloud API.
- [API Rate Limits for the Boole AI Cloud: 60 req/sec](https://docs.booleinference.com/account/rate-limits.md): Understand default rate limits on the Boole AI cloud API, handle 429 errors gracefully, and request a higher limit for high-volume workloads.
- [Troubleshoot Boole AI: Startup, Auth, and Performance](https://docs.booleinference.com/support/troubleshooting.md): Solutions for the most common Boole AI issues — local binary startup failures, API authentication errors, rate limits, and performance problems.
- [Boole AI FAQ: Pricing, Privacy, and Technical Questions](https://docs.booleinference.com/support/faq.md): Answers to common questions about Boole AI's inference engine, pricing, data privacy, model availability, and OpenAI compatibility.
- [Contact Boole AI Support, Billing, and Security Teams](https://docs.booleinference.com/support/contact.md): All support channels for Boole AI — technical help, billing questions, security vulnerability reports, and general inquiries with expected response times.
- [Boole AI REST API – Endpoints, Errors, and Base URLs](https://docs.booleinference.com/api-reference/overview.md): Explore the Boole AI OpenAI-compatible REST API: base URLs for cloud and local, versioning, request and response formats, and all available endpoints.
- [Boole AI API Authentication – Keys, Headers, and SDKs](https://docs.booleinference.com/api-reference/authentication.md): Learn how to pass API keys in request headers, handle authentication errors, and configure local binary deployments that require no auth.
- [Chat Completions – Streaming, Tools, and Structured Output](https://docs.booleinference.com/api-reference/chat-completions.md): Generate chat responses with the Boole AI chat completions endpoint — covering request parameters, streaming, tool calls, and structured JSON output.
- [Legacy Text Completions – Prompt-In, Completion-Out API](https://docs.booleinference.com/api-reference/completions.md): Use the legacy text completions endpoint for prompt-in, completion-out workflows — parameters, an example request, and when to prefer chat completions.
- [Boole AI Models Endpoint – List All 42 Available Models](https://docs.booleinference.com/api-reference/models.md): Retrieve all available Boole AI model slugs with the models endpoint, and learn how to use the returned IDs in chat and completion requests.
- [Boole AI Audio Transcriptions – Whisper Large v3 Endpoint](https://docs.booleinference.com/api-reference/audio.md): Transcribe audio files with the Boole AI Whisper Large v3 endpoint — accepted formats, multipart request parameters, response schema, and pricing.