Integration

Mistral AI integration

European AI company providing powerful open and commercial language models. Access efficient models optimized for various use cases including chat, coding, reasoning, OCR, audio transcription, and moderation. Features include function calling, structured outputs, batch processing, and competitive performance.

Connect Mistral AI How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Mistral AI.Built from the 31 Mistral AI tools below, on the connection you add once.

Common Mistral AI use cases

file management
job monitoring
model organization
progress monitoring
model lifecycle management
cost control
metadata lookup
batch management
capability check
error recovery

What you can do with Mistral AI

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

File, 6 operations

delete_fileDelete fileDELETEDeletes an uploaded file. Remove files from your account when no longer needed.
download_fileDownload fileGETDownloads file content. Retrieve the binary content of an uploaded file.
get_file_signed_urlGet file signed urlGETGets a signed URL for file download. Generate a temporary URL for direct file access.
list_filesList filesGETLists uploaded files. View all files with metadata, status, and purpose information.
retrieve_fileRetrieve fileGETRetrieves file metadata. Get details about an uploaded file including size, status, and purpose.
upload_fileUpload filePOSTUploads a file. Submit data files for use in fine-tuning, batch processing, or OCR.

Model, 6 operations

archive_fine_tuned_modelArchive fine tuned modelPOSTArchives a fine-tuned model. Temporarily disable a model without deleting it.
delete_modelDelete modelDELETEDeletes a fine-tuned model. Remove custom models from your account when no longer needed.
list_modelsList modelsGETLists available Mistral models. View all accessible models including base models and fine-tuned versions with metadata.
retrieve_modelRetrieve modelGETRetrieves details of a specific model. View model metadata including capabilities and creation date.
unarchive_fine_tuned_modelUnarchive fine tuned modelDELETEUnarchives a fine-tuned model. Restore an archived model for inference use.
update_fine_tuned_modelUpdate fine tuned modelPATCHUpdates a fine-tuned model's name or description. Modify metadata for custom models.

Fine tuning, 5 operations

cancel_fine_tuning_jobCancel fine tuning jobPOSTCancels a fine-tuning job. Stop an in-progress training job when no longer needed.
create_fine_tuning_jobCreate fine tuning jobPOSTCreates a fine-tuning job. Train custom Mistral models on your data with configurable hyperparameters.
get_fine_tuning_jobGet fine tuning jobGETGets fine-tuning job details. Retrieve status, progress, metrics, and configuration for a specific training job.
list_fine_tuning_jobsList fine tuning jobsGETLists fine-tuning jobs. View all training jobs with status, progress, and configuration details.
start_fine_tuning_jobStart fine tuning jobPOSTStarts a validated fine-tuning job. Begin training after job validation is complete.

Batch, 4 operations

cancel_batch_jobCancel batch jobPOSTCancels a batch job. Stop an in-progress batch processing job.
create_batch_jobCreate batch jobPOSTCreates a batch inference job. Process many requests asynchronously at lower cost.
get_batch_jobGet batch jobGETGets batch job details. Retrieve status, progress, and results for a specific batch job.
list_batch_jobsList batch jobsGETLists batch jobs. View all batch processing jobs with status and progress information.

Classification, 2 operations

chat_classificationsChat classificationsPOSTClassifies chat conversations using custom classifiers. Categorize conversation content with fine-tuned models.
classificationsClassificationsPOSTClassifies text using custom or built-in classifiers. Categorize text with fine-tuned classification models.

Moderation, 2 operations

chat_moderationsChat moderationsPOSTClassifies chat conversations for content moderation. Analyze multi-turn conversations for policy violations.
moderationsModerationsPOSTClassifies text for content moderation. Detect harmful content across categories including sexual, hate, violence, and PII.

Agent, 1 operation

agents_completionsAgents completionsPOSTCreates agent completions. Generate responses using pre-configured Mistral agents with custom instructions and tools.

Audio, 1 operation

audio_transcriptionsAudio transcriptionsPOSTTranscribes audio to text with Voxtral. Convert speech to text with optional speaker diarization and timestamps.

Chat, 1 operation

chat_completionsChat completionsPOSTCreates chat completions with Mistral models. Send messages for AI-powered conversational responses with tool calling support.

Code, 1 operation

fim_completionsFim completionsPOSTFill-in-the-middle code completion with Codestral. Generate code to insert between prefix and suffix for intelligent code infilling.

Embedding, 1 operation

embeddingsEmbeddingsPOSTCreates text embeddings with Mistral. Convert text into vector representations for semantic search and similarity matching.

Ocr, 1 operation

ocrOcrPOSTProcesses documents with OCR. Extract text, tables, and images from PDFs and images with high accuracy.

Use Mistral AI from Claude Code, Cursor or Codex

Connect Mistral AI in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Mistral AI operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Mistral AI

Create your workspace
Sign up free. Nothing to install.
Connect Mistral AI once
Add your Mistral AI connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Mistral AI integration FAQ

What can you do with the Mistral AI integration?

LiveContext exposes 31 operations on Mistral AI, covering file, model, fine tuning and batch. Common uses include file management, job monitoring and model organization.