All Providers Quick Reference
BLACK HOLE includes 60+ Providers. This page provides an overview table. Once you find your target Provider, follow the instructions to enter your key to start using it. Providers with dedicated documentation have jump links; others are configured using the general steps (Provider Overview).
Usage Steps
- Find your target Provider (use Ctrl/⌘+F to search quickly)
- Click Official Website to register an account and obtain an API Key
- Find the corresponding Provider in BLACK HOLE
Settings → Model Provider, enter the key, and click "Sync models" - Complete the configuration
One-Sentence Decision Guide
| Your Need | Recommended Direction |
|---|---|
| Quick start for beginners, avoiding complex processes | BLACK HOLE IN or BLACK HOLE |
| Strong value for coding and long context | DeepSeek / Moonshot (Kimi) / Z.ai (Zhipu) / MiniMax |
| Leading frontier models | OpenAI / Anthropic / Gemini |
| One key for 200+ providers | OpenRouter |
| Fully local, privacy-sensitive | Ollama / LM Studio |
| Enterprise compliance | Azure OpenAI / AWS Bedrock |
| Using Agents | Anthropic / BLACK HOLE IN (must support Anthropic protocol) |
Chinese Model Providers
Model makers based in China. Several offer international platforms (linked below); strong Chinese-language support and relatively affordable pricing.
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| DeepSeek | Best value for coding and reasoning | deepseek.com | → |
| Moonshot AI (Kimi) | Ultra-long context (up to 2 million words) | moonshot.ai | → |
| ZhiPu (Z.ai) | GLM series, multimodal, Anthropic-compatible for Agents | z.ai | → |
| MiniMax | Multimodal (voice, video) | minimax.io | → |
| StepFun | StepFun (Jieyue Xingchen) | stepfun.com | — |
| LongCat | Meituan LongCat series | longcat.chat | — |
| Xiaomi MiMo | Xiaomi large models | mimo.mi.com | — |
Major International Providers
Frontier models from the leading US and European labs.
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| OpenAI | GPT series | openai.com | → |
| Anthropic | Claude series, top choice for Agents | anthropic.com | → |
| Gemini (Google) | Google large models | aistudio.google.com | → |
| Azure OpenAI | Microsoft-hosted OpenAI, enterprise compliance | portal.azure.com | → |
| VertexAI | Google Cloud hosted | cloud.google.com | — |
| AWS Bedrock | Amazon-hosted multi-provider models | aws.amazon.com/bedrock | — |
| Mistral | Representative of European open-source models | mistral.ai | → |
| Grok (xAI) | Elon Musk's xAI, built-in web access | x.ai | → |
| Perplexity | Search-enhanced conversation | perplexity.ai | → |
Gateways / Aggregators
Access multiple models with one key, centralized account management.
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| BLACK HOLE | BLACK HOLE official free trial | — | → |
| BLACK HOLE IN | BLACK HOLE official paid gateway, dual endpoints (OpenAI + Anthropic) | Setup guide | → |
| OpenRouter | Largest aggregator, 200+ models | openrouter.ai | → |
| AiHubMix | Multi-vendor aggregator | aihubmix.com | — |
| Poe | Quora's AI marketplace | poe.com | — |
| Vercel AI Gateway | Vercel's gateway | vercel.com/ai | — |
Ultra-Low Latency / High-Throughput Inference Services
Suitable for scenarios requiring "speed" (IM bots, real-time translation, etc.).
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| Groq | LPU hardware, millisecond-level response | groq.com | → |
| Cerebras AI | Proprietary chips, ultra-large context | cerebras.ai | — |
| Together | Centralized hosting for open-source models | together.ai | — |
| Fireworks | Optimized inference for open-source models | fireworks.ai | — |
Open-Source Model Hosting
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| SiliconFlow | Large-scale open-source model hosting | siliconflow.com | → |
Embedding / Reranking Only
Used exclusively for embeddings or reranking, paired with Knowledge Bases / Global Memory.
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| Jina | Embeddings, reranking, CLIP, large free quota | jina.ai | — |
| VoyageAI | Embedding / Reranking specialist | voyageai.com | — |
Local Inference
Fully offline, protects privacy.
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| Ollama | Command-line local inference, most popular | ollama.com | → |
| LM Studio | GUI local inference, Apple Silicon friendly | lmstudio.ai | → |
| GPUStack | Enterprise-grade local inference | gpustack.ai | — |
| OpenVINO Model Server | Intel-accelerated local inference | openvino.ai | — |
Model Platforms / Others
| Provider | Key Feature | Official Website | Dedicated Doc |
|---|---|---|---|
| Hugging Face | World's largest open-source model community | huggingface.co | — |
| GitHub Copilot | Microsoft GitHub coding assistant | github.com/features/copilot | → |
| GitHub Models | GitHub model marketplace (Beta) | github.com/marketplace/models | — |
| nvidia | NVIDIA NIM inference | nvidia.com | — |
Custom Providers
If the service you use is not in the list above but supports any of the OpenAI-compatible / Anthropic-compatible / Gemini-compatible protocols, you can add it via Custom Provider.
Still Not Sure Which to Choose?
Go directly with BLACK HOLE IN or BLACK HOLE — best for beginners to get started quickly. Switch later if you need advanced features.
Get Help and Submit Feedback
If you have any questions, bugs, or feature improvement suggestions during configuration or usage, please refer to the official channels provided in Feedback and Suggestions.