Mistral AI
Mistral chat and reasoning models, mistral-embed embeddings and Mistral OCR over api.mistral.ai.
OCNORA ships 10 typed Mistral AI operations. Each node has a schema-driven form, input and output tables beside its settings, and is pre-flighted by Workflow Health before your first real run. Endpoints not covered by a typed node are called at https://api.mistral.ai/v1 through the HTTP node with the same credential.
Before you connect Mistral AI
- Authentication
- API key
- Credential
- {"api_key": "…"} — a Mistral API key
- Connection test
- Available: the stored credential can be checked against the provider when you add it. This is not a record that a test was run or passed.
What you can do with Mistral AI
Operations, grouped by what they do to your data.
Create and send 2
Read and search 5
Delete and cancel 1
Other operations 2
A sample Mistral AI workflow
- 1A core triggerStart the run from a chat, form, manual, schedule, webhook, workflow trigger — no Mistral AI trigger is needed.
- 2Get File Download URLmistral.file_urlMint a temporary signed download URL for an uploaded file — the usual way to hand a stored PDF to the OCR node.
- 3Chat Completionmistral.chat_completionSend a prompt or a full message list to a Mistral chat model and return the assistant's answer together with the token usage.
An outline built from this provider’s node contracts, not a recorded run. Each step’s output fields are available to the next in the field picker.
Every node below has a reference page: what it does, the connection it needs, its config fields with types, constraints and examples, and the shapes it emits.
Operations 10
- Chat CompletionSend a prompt or a full message list to a Mistral chat model and return the assistant's answer together with the token usage.mistral.chat_completion
- Delete FilePermanently delete one uploaded file from the Mistral workspace.mistral.delete_file
- Create EmbeddingsTurn one string or a list of strings into embedding vectors with a Mistral embedding model such as mistral-embed.mistral.embeddings
- Get File Download URLMint a temporary signed download URL for an uploaded file — the usual way to hand a stored PDF to the OCR node.mistral.file_url
- Get FileFetch one uploaded file's record — its name, size, purpose and MIME type.mistral.get_file
- Get ModelFetch one model card, including its capabilities and context length.mistral.get_model
- List FilesList one page of the files uploaded to the Mistral workspace.mistral.list_files
- List ModelsList every Mistral model the connection's API key is allowed to call.mistral.list_models
- OCR DocumentRun Mistral OCR over a PDF or image and return the text of every page as Markdown, keeping the document's layout and tables.mistral.ocr
- Upload FileUpload a file to the Mistral workspace for fine-tuning, batch inference or OCR, and return the file id to reference later.mistral.upload_file
Mistral AI questions
- How does OCNORA authenticate with Mistral AI?
- With a stored API key credential, shaped {"api_key": "…"} — a Mistral API key. A connection test can check it when you add it.
- What can I automate with Mistral AI?
- 10 typed operations, each with a reference page listing its config fields and the shapes it emits.
- What if the Mistral AI operation I need is not listed?
- Call https://api.mistral.ai/v1 from the HTTP node with the same credential, or describe the step to the AI builder, which asks our team for a typed node when one is missing.
- Are there templates that use Mistral AI?
- Not yet. Start from a blank workflow, or describe the workflow to Build with AI.
- How are Mistral AI calls controlled?
- Every call and every run step is audited, runs count against the tenant’s token and USD budgets, and Workflow Health pre-flights the workflow when you save it.
More in AI & models
See your first Mistral AI workflow run.
Book a technical demo. We add the connection, pick a template or describe the workflow to Build with AI, and Workflow Health checks it before it runs.