# Darkbloom

## Docs

- [Transcribe audio files with Darkbloom's API](https://docs.darkbloom.dev/api/audio-transcription.md): POST /v1/audio/transcriptions transcribes audio to text using the OpenAI-compatible Whisper endpoint, served by attested Apple Silicon providers.
- [Authenticate requests to the Darkbloom API](https://docs.darkbloom.dev/api/authentication.md): Create and manage API keys for the Darkbloom inference API. Keys start with eigeninference- and are passed as Authorization: Bearer tokens on every request.
- [Send chat completions with the Darkbloom API](https://docs.darkbloom.dev/api/chat-completions.md): Use POST /v1/chat/completions to run multi-turn conversations on Darkbloom. Fully OpenAI-compatible, with streaming, system prompts, and trust headers.
- [Generate images from text with Darkbloom's API](https://docs.darkbloom.dev/api/image-generation.md): POST /v1/images/generations generates images from a text prompt using the OpenAI-compatible image endpoint, served by attested Apple Silicon providers.
- [Browse and select Darkbloom inference models](https://docs.darkbloom.dev/api/models.md): Use GET /v1/models to see which models are online, compare capabilities and pricing, and choose the right model for your workload and budget.
- [Add credits to your Darkbloom account](https://docs.darkbloom.dev/billing/add-credits.md): Load a prepaid credit balance using a credit or debit card through Stripe. Credits apply immediately after payment and never expire.
- [Darkbloom pricing: per-token rates for every model](https://docs.darkbloom.dev/billing/pricing.md): Token pricing for every model on Darkbloom, how the prepaid credit balance works, and how to check your current rates and usage programmatically.
- [Darkbloom referral program: share and earn](https://docs.darkbloom.dev/billing/referrals.md): Create a personal referral code, share it with others, and track your referral activity. Manage everything via the Darkbloom API or web console.
- [Darkbloom: Decentralized Private AI Inference](https://docs.darkbloom.dev/introduction.md): Darkbloom routes AI to idle Apple Silicon Macs. Get an OpenAI-compatible API with hardware-level privacy, or earn by sharing your Mac's compute.
- [darkbloom CLI: complete command reference](https://docs.darkbloom.dev/provider/cli-reference.md): Complete reference for every darkbloom subcommand — serve, start, stop, status, doctor, models, earnings, login, and more — with flags and usage examples.
- [Understanding and withdrawing your earnings](https://docs.darkbloom.dev/provider/earnings.md): How provider earnings are calculated per model, how to check your balance via CLI or web console, and how to withdraw via Stripe Connect.
- [Installing and setting up the provider agent](https://docs.darkbloom.dev/provider/install.md): Install the Darkbloom provider agent on your Apple Silicon Mac, link your account, pick a model, and start earning in a few minutes.
- [Manage your provider with the Darkbloom Mac app](https://docs.darkbloom.dev/provider/macos-app.md): The native macOS menu bar app lets you start and stop your provider, monitor throughput, view earnings, configure scheduling, and enable idle detection.
- [Earn by sharing your Mac's compute on Darkbloom](https://docs.darkbloom.dev/provider/overview.md): Run AI inference on your idle Apple Silicon Mac and earn 100% of the revenue. No platform fee, no port forwarding, and consumers cannot read your data.
- [Schedule when your Mac serves inference requests](https://docs.darkbloom.dev/provider/scheduling.md): Set specific days and hours when your Mac serves requests. Outside scheduled windows, the provider disconnects and frees GPU memory for your own use.
- [Quickstart: call the Darkbloom API in 5 minutes](https://docs.darkbloom.dev/quickstart-consumer.md): Get an API key, send your first chat completion, and list available models using any OpenAI-compatible SDK. Works with Python, Node.js, and curl.
- [Quickstart: become a Darkbloom inference provider](https://docs.darkbloom.dev/quickstart-provider.md): Turn your idle Apple Silicon Mac into a Darkbloom provider. Install the agent, link your account, pick a model, and start earning in about 10 minutes.
- [API key management — POST and DELETE /v1/auth/keys](https://docs.darkbloom.dev/reference/api-keys.md): POST /v1/auth/keys creates a new API key; DELETE /v1/auth/keys revokes one. Both require an interactive Privy browser session — API key auth is not accepted.
- [Provider attestation — GET /v1/providers/attestation](https://docs.darkbloom.dev/reference/attestation.md): GET /v1/providers/attestation — public attestation data. No auth required. Returns trust level, SE public key, and MDA chain for independent verification.
- [Account balance — GET /v1/payments/balance](https://docs.darkbloom.dev/reference/balance.md): GET /v1/payments/balance — returns your current account balance. Returns balance_micro_usd, balance_usd, withdrawable_micro_usd, and withdrawable_usd.
- [Chat completions — POST /v1/chat/completions](https://docs.darkbloom.dev/reference/chat-completions.md): POST /v1/chat/completions — generates replies from a message history. Accepts model, messages, stream, temperature. Returns a chat completion or SSE stream.
- [Text completions — POST /v1/completions](https://docs.darkbloom.dev/reference/completions.md): POST /v1/completions — legacy text completion endpoint. Accepts model, prompt, max_tokens, temperature, and stream. Returns a completion object or SSE stream.
- [Anthropic Messages API — POST /v1/messages](https://docs.darkbloom.dev/reference/messages.md): POST /v1/messages — Anthropic-compatible endpoint. Accepts model, messages, max_tokens, and system. Returns an Anthropic-format content array response.
- [Available models — GET /v1/models](https://docs.darkbloom.dev/reference/models.md): GET /v1/models — returns available inference models with provider count, attestation status, and trust level. Compatible with OpenAI's model list format.
- [Network stats — /v1/stats, /v1/leaderboard](https://docs.darkbloom.dev/reference/stats.md): Public endpoints for Darkbloom network statistics. No auth required. Returns active providers, token totals, leaderboard rankings, and network-wide totals.
- [Usage history — GET /v1/payments/usage](https://docs.darkbloom.dev/reference/usage.md): GET /v1/payments/usage — returns your inference usage history. Each entry includes model, token counts, cost in micro-USD, and a timestamp.
- [Verifying provider attestation on Darkbloom](https://docs.darkbloom.dev/security/attestation.md): Darkbloom's four-layer attestation proves every provider's security posture is intact. Learn how to verify attestation data and read per-request trust headers.
- [How Darkbloom keeps your prompts private](https://docs.darkbloom.dev/security/overview.md): Darkbloom uses E2E encryption, macOS Hardened Runtime, and Secure Enclave attestation so Mac owners running inference cannot read your prompts.
- [Understanding provider trust levels on Darkbloom](https://docs.darkbloom.dev/security/trust-levels.md): What self_signed and hardware trust levels mean for your privacy, how each is verified, and how to check the trust level of any inference response.