Hugging Face
Hugging Face Inference API gateway
Hugging Face's Inference API gives every public model on the Hub a hosted endpoint — text generation, classification, embeddings, image generation, audio transcription, all callable with a single API key. Tiny Command exposes four actions, no triggers: Chat Completion (against text-generation models, with the OpenAI-compatible chat-completions shape that Hugging Face's TGI-served models implement), Text Classification (NLP classifiers — sentiment, toxicity, NER, intent — pick any classifier model from the Hub), Feature Extraction (Embeddings) (sentence embeddings from sentence-transformers and BGE models), Text to Image (Stable Diffusion variants, Flux, and other image-gen models). The connection uses a Hugging Face access token from huggingface.co/settings/tokens with the inference scope. The "any model on the Hub" promise has trade-offs — free-tier inference is rate-limited and uses shared compute (variable latency); for production, use Inference Endpoints (dedicated managed deployments) or Inference Providers (HF's partner-hosted hot models with better SLAs).
Do anything Hugging Face can do, from a workflow.
Every action accepts dynamic inputs from upstream nodes, whether that's an AI output, a form field, or a search result.
| Action | What it does |
|---|---|
| Hugging Face Chat Completion | Runs chat completion against any text-generation model on Hugging Face Hub that supports the TGI server. OpenAI-compatible message-array shape. Model selection via model ID (e.g., meta-llama/Llama-3.3-70B-Instruct). |
| HF Feature Extraction (Embeddings) | Generates sentence embeddings from any sentence-transformers or BGE-class model on the HF Hub. For RAG-pipeline vector generation when you want a specific HF-hosted embedding model. |
| HF Text Classification | Runs any classifier model from HF Hub on text input — sentiment, toxicity, NER, intent. Pick the right classifier for your use case from the broad Hub catalog. |
| HF Text to Image | Generates images from text using any HF-hosted image model (SDXL, SD3.5, Flux variants, community fine-tunes). For accessing niche or specific image models from the broad HF catalog. |
Pre-built Hugging Face workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
AI-triage every Hugging Face event, ping the right channel only when it matters.
Every event matching a filter, appended to a running spreadsheet.
Turn Hugging Face into a Notion-backed source of truth, auto-tagged.
Three things worth knowing.
Tiny Command counts a run the moment a trigger fires. Filtering early means only matching events spend your usage budget.
Connect Hugging Face once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Hugging Face field shows up in the visual picker for downstream nodes. The raw payload is there for power users, optional for everyone else.
Questions about the Hugging Face integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect Hugging Face to Tiny Command?
What Hugging Face triggers does Tiny Command support?
What Hugging Face actions can I run from a workflow?
Is the Hugging Face integration real-time?
Do I need to write code to use Hugging Face with Tiny Command?
How much does the Hugging Face integration cost?
More ai & ml apps people connect.
Same category as Hugging Face, ordered by how often teams pair them. Hover the carousel to pause.
Do more with Hugging Face.
Wire it to Slack, Notion, HubSpot, Stripe, or any of the other 438 apps in our catalog. Setup takes roughly two minutes. Free to try, no credit card.
