| <div class="grid lg:grid-cols-3 gap-x-4 gap-y-7"> |
| <p class="lg:col-span-3"><b>GPUs and inference for your agents.</b> <a href="https://www.runcrate.ai/?utm_source=huggingface&utm_medium=directory&utm_campaign=gpu_pricing" class="underline">runcrate.ai</a></p> |
| <div class="lg:col-span-3"> |
| <ul> |
| <li><b>Inference:</b> open models (DeepSeek, Qwen, Llama, Kimi, FLUX, Whisper) behind one OpenAI-compatible API at <code>https://api.runcrate.ai/v1</code>, priced per token, image, second or minute depending on the model. <a href="https://www.runcrate.ai/inference/pricing?utm_source=huggingface&utm_medium=directory&utm_campaign=gpu_pricing" class="underline">Models and prices</a></li> |
| <li><b>GPU marketplace:</b> rent H100, H200, A100, L40S, RTX 4090 and more with SSH, priced per GPU-hour and billed by the second on most GPUs, by the minute on a few. <a href="https://www.runcrate.ai/pricing?utm_source=huggingface&utm_medium=directory&utm_campaign=gpu_pricing" class="underline">GPU pricing</a></li> |
| <li><b>Built for agents:</b> a remote MCP server at <code>https://mcp.runcrate.ai/mcp</code> (OAuth sign-in, no key) lets Claude Code, Cursor or Codex launch a GPU, run commands on it and shut it down. <a href="https://www.runcrate.ai/docs/mcp/setup?utm_source=huggingface&utm_medium=directory&utm_campaign=mcp" class="underline">MCP setup</a></li> |
| <li><b>Tools:</b> CLI (<code>brew install aeonmindai/tap/runcrate</code>), Python (<code>pip install runcrate-sdk</code>) and TypeScript (<code>npm i @runcrate/sdk</code>) SDKs.</li> |
| </ul> |
| </div> |
| <p class="lg:col-span-3">Try the models in the <a href="https://huggingface.co/spaces/runcrate/inference-playground" class="underline">inference playground</a> with your own API key, or run the <a href="https://colab.research.google.com/drive/1r5gpncUfDCjHwHOd53nypbblCDSLvips" class="underline">Colab quickstart</a> (OpenAI client, LangChain, LlamaIndex, DSPy). Contact: hello@runcrate.ai</p> |
| </div> |
|
|
