Mistral AI
Mistral AI chat, embeddings, OCR, and tools
Mistral AI is the French LLM lab whose open-weight and hosted models are popular alternatives to OpenAI and Anthropic — especially for EU teams with data-residency requirements and for cost-sensitive deployments where Mixtral 8x22B or the Mistral Small tier hits the price/performance sweet spot. Tiny Command exposes six actions: Chat Completion (against mistral-small, mistral-medium, mistral-large, codestral, the Mixtral family, and pixtral for vision), Chat with Tools (function-calling, OpenAI-compatible schema), Create Embedding (mistral-embed for semantic search workflows), Moderate Text (the mistral-moderation classifier for safety filtering), OCR (the mistral-ocr endpoint that takes a document URL or base64 and returns Markdown — strong on PDFs with mixed text/tables), and List Models. The connection uses a Mistral API key from console.mistral.ai. The Chat APIs follow the OpenAI message-array shape (system, user, assistant), so workflows that have a Chat Completion structure already can swap models with minimal rewriting.
Do anything Mistral AI 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 |
|---|---|
| Mistral Chat Completion | Runs chat completion against Mistral's hosted models (Small, Medium, Large, Codestral, Mixtral variants, Pixtral). OpenAI-compatible shape. EU-hosted inference for data-residency-conscious workflows. |
| Mistral Chat with Tools | Chat completion with function-calling enabled. OpenAI-compatible tools array. Response includes tool_calls when the model decides to call one. Parallel tool calls supported. |
| Mistral Embedding | Generates embeddings with mistral-embed. For RAG-pipeline vector generation when you want EU-hosted embedding inference. |
| List Mistral Models | Returns the Mistral model catalog. Pin specific versions for reproducibility; "latest" aliases float as Mistral ships new generations. |
| Mistral Moderate Text | Returns category scores across harm types (violence, hate, sexual, self-harm, etc.). For pre-filter step before higher-cost LLM calls or for content-moderation workflows in user-generated content. |
| Mistral OCR (Document → Markdown) | Mistral's specialised OCR model — converts PDFs/images to clean Markdown preserving headings, tables, multi-column layout. Better than general vision-LLM OCR for structured document processing. |
Pre-built Mistral AI 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 Mistral AI once and every workflow on your account can use its triggers and actions. You don't have to re-auth per workflow.
Every Mistral AI 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 Mistral AI integration.
If we missed yours, ping support. We usually reply within an hour.
How do I connect Mistral AI to Tiny Command?
What Mistral AI triggers does Tiny Command support?
What Mistral AI actions can I run from a workflow?
Is the Mistral AI integration real-time?
Do I need to write code to use Mistral AI with Tiny Command?
How much does the Mistral AI integration cost?
More ai & ml apps people connect.
Same category as Mistral AI, ordered by how often teams pair them. Hover the carousel to pause.
Do more with Mistral AI.
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.
