knoten / builtin / ai / aidependencies / llm
Chat Mistral
Run Mistral open and frontier models for text generation.
Dieser Inhalt ist noch nicht in deiner Sprache verfügbar.
Give an AI node access to Mistral AI’s open and frontier models, using your own Mistral API key.
What it does
Section titled “What it does”Chat Mistral is a model you plug into the Model slot of an AI node, such as the Tools Agent or Basic LLM Chain. It does not run on its own and has no output. When the AI node runs, it sends its messages to Mistral with your key and gets the reply back.
- Temperature is 0 when you leave it empty, so answers are focused and repeatable.
- Replies are capped at Max Tokens (4096 by default).
- A failed request is retried up to Max Retries times (2 by default). A request that gets no answer within 60 seconds fails.
When to use it
Section titled “When to use it”- You prefer a European AI provider.
- Writing and translating text in a workflow with your Mistral account.
- A small, cheap model for simple jobs and a large one for harder ones, from the same provider.
Inputs and settings
Section titled “Inputs and settings”| Einstellung | Typ | Was es bewirkt |
|---|---|---|
| Model (erforderlich) | Text | The Mistral model to use, e.g. mistral-large-latest. |
| Authentication (erforderlich) | Credential | Use your Mistral API key as a Bearer token. |
| Options | Group | The options to use with the model. |
| Options › Temperature | Number | The temperature to use for the model. |
| Options › Max Retries | Number | The maximum number of retries to use for the model. Standard: 2 |
| Options › Max Tokens | Number | The most tokens the model may generate in one reply. Defaults to 4096, which keeps providers from reserving credit for the whole output window. Standard: 4096 |
Type the Model id as Mistral names it, for example mistral-large-latest or mistral-small-latest. The -latest ids always point to the newest version.
Outputs
Section titled “Outputs”This node has no output port. It plugs into a slot on another node instead of passing items along.
- Model slot of Tools Agent, Q&A Agent, RAG Agent, Basic LLM Chain, Indexer, Text Classifier, Sentiment Analysis, Summarization, Information Extractor, Guardrails, Auto-fixing Output Parser
The AI node you connect it to produces the output. Chat Mistral only decides which model answers.
Dependencies and credentials
Section titled “Dependencies and credentials”- Authentication (connection): required. See Connect Mistral.
In Authentication, use a Bearer Token credential that holds your Mistral API key. Create the key on the API Keys page of the Mistral console (La Plateforme). See Create a credential.
Example workflow
Section titled “Example workflow”- A Context Menu trigger on selected text.
- Basic LLM Chain with Prompt
Translate into French, keep the tone: {{ $input.selectionText }}. - Chat Mistral in its Model slot, Model
mistral-small-latest. - Clipboard Write with Text
{{ $input.response }}.
Common issues
Section titled “Common issues”- “Model parameter is required and cannot be empty”. Fill in Model.
- A 401 error. The key is wrong or revoked. Create a new key and update the credential.
- A 429 error. You hit your plan’s rate limit. Send fewer items at once, or upgrade the plan.
- An “invalid model” error. The model id is misspelled. Copy it from Mistral’s model list.
Related nodes
Section titled “Related nodes”- Basic LLM Chain: send one prompt and get a reply.
- Tools Agent: an agent that can use tools and memory.
- Translate: translate on your device, without a key.