OpenAI
Drop chat, embeddings, vision, voice into any workflow
OpenAI is a utility layer on Tiny Command, no triggers, just sixteen high-leverage actions that other workflows reach for the moment they need intelligence. Chat Completion and Chat with Tools handle conversational responses and function calling. Create Embedding produces vectors for similarity search. Analyze Image, Generate Speech, and Transcribe Audio handle the modalities beyond text. Moderate Text protects user-facing surfaces from policy violations. Create Batch and Get Batch unlock the 50%-cheaper async pricing for non-realtime workloads, and Create Vector Store gives you a managed embedding store for retrieval-augmented workflows. Model selection (gpt-4o, gpt-4o-mini, o1, o3) and temperature/max-tokens are exposed on every action, so a single workflow can route different stages to different model tiers. The connection uses your own OpenAI API key, so token usage shows up in your OpenAI dashboard the same way it would for a direct API call.
Do anything OpenAI 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 |
|---|---|
| Analyze Image | Analyzes an image using GPT-4o vision, accepting a URL or base64-encoded image plus a text prompt. Use for OCR, chart extraction, alt-text generation, or visual QA. |
| Chat Completion | Sends a message and gets a response from an OpenAI chat model (gpt-4o, gpt-4o-mini, o-series, etc.). The standard chat-completion action; supports system prompts, temperature, and stop sequences. |
| Chat with Tools | Chat completion with tool/function calling enabled. The model may return tool_calls instead of (or in addition to) text; you execute them and feed results back as tool messages for the next turn. |
| Create Batch | Submits a batch of OpenAI requests at a 50% cost discount with a 24-hour SLA. Requires an uploaded JSONL file id with one request per line. Perfect for bulk classification or embedding jobs. |
| Create Embedding | Generates vector embeddings for text using text-embedding-3-small or text-embedding-3-large. The de-facto embeddings default for RAG and semantic search. |
| Create Image (DALL-E) | Generates images from a text prompt using DALL-E (or gpt-image-1). Supports size, quality, and style controls; returns a URL or base64-encoded image. |
| Create Response | Creates a model response using OpenAI's Responses API, the unified endpoint that supersedes chat-completions for new use cases. Supports tools, vision, structured output, and file inputs in a single call. |
| Create Vector Store | Creates a vector store (used by the File Search tool in Responses/Assistants). OpenAI handles chunking, embedding, and indexing of any files you attach. |
| Delete File | Deletes a previously uploaded file from your OpenAI storage. Use to clean up after a batch job or to remove PII for compliance. |
| Edit Image | Edits an image with a prompt and optional mask using gpt-image-1 (or dall-e-2). Supports inpainting (mask defines the region to regenerate). Great for product retouching or asset variations. |
| Generate Speech (TTS) | Converts text to speech audio using OpenAI's TTS models, returning audio bytes (mp3 by default). Supports multiple voices (alloy, echo, fable, onyx, nova, shimmer). |
| Get Batch | Retrieves a batch by ID to check status (validating, in_progress, finalizing, completed, failed) and download the output_file_id when complete. Poll every few minutes. |
| List Files | Lists all uploaded files in your OpenAI workspace with their purpose (assistants, batch, fine-tune) and size. Used for cleanup and audit. |
| List Models | Lists available OpenAI models with their IDs and ownership. Useful for surfacing a dynamic model picker. |
| Moderate Text | Checks text against OpenAI's moderation endpoint for harmful content (hate, harassment, self-harm, sexual, violence), with per-category scores. Free to use; gate user-generated content with this. |
| Transcribe Audio (Whisper) | Transcribes audio into text using OpenAI Whisper. Supports mp3, mp4, mpeg, mpga, m4a, wav, and webm; up to 25 MB per file. Also supports translation to English. |
Pre-built OpenAI workflows.
Clone any recipe and customize it in one click. Every recipe is fully editable.
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 OpenAI once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every OpenAI 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 OpenAI integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect OpenAI to Tiny Command?
What OpenAI triggers does Tiny Command support?
What OpenAI actions can I run from a workflow?
Is the OpenAI integration real-time?
Do I need to write code to use OpenAI with Tiny Command?
How much does the OpenAI integration cost?
More ai & ml apps people connect.
Same category as OpenAI, ordered by how often teams pair them. Hover the carousel to pause.
Do more with OpenAI.
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.
