Mistral AI is a research lab building state-of-the-art open-source language models and providing APIs for developers and enterprises to integrate these models into their applications.
Mistral AI is a research lab building state-of-the-art open-source language models and providing APIs for developers and enterprises to integrate these models into their applications. On Nagent, Mistral AI is exposed as a fully-configurable artificial intelligence integration that any agent can call — 54 actions, and API key authentication. No code is required to wire Mistral AI into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Mistral AI to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Mistral AI into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Mistral AI, with input parameters and output schema. Drop these into any step of an agent built in Helix.
MISTRAL_AI_APPEND_TO_CONVERSATIONTool to append new entries to an existing conversation in Mistral AI. Use when you need to continue a conversation by adding new messages or inputs. This is a beta endpoint.
Input parameters
Whether to persist the conversation results to the server. Defaults to true
New input to append to the conversation. Can be a string (simple text input) or an array of entry objects (MessageInputEntry, MessageOutputEntry, FunctionResultEntry, etc.)
White-listed arguments from the completion API to configure the response generation (e.g., temperature, max_tokens)
ID of the conversation to which entries will be appended
Handoff execution mode for agent handoffs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_AGENTTool to create a new AI agent with custom configuration (Beta). Use when you need to create an agent with specific model, name, instructions, and tools.
Input parameters
Name of the agent
Model ID to use for the agent (e.g., 'mistral-large-latest', 'mistral-small-latest')
List of tools available to the agent. Can include function tools, web search, code interpreter, image generation, or document library tools
Optional handoff configuration for agent-to-agent transfers
Optional metadata to attach to the agent
Optional description of the agent's purpose and capabilities
System instructions that guide the agent's behavior during conversations
White-listed arguments from the completion API.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_AGENTS_COMPLETIONTool to generate completions using a Mistral AI agent with specific instructions and tools. Use when you need an agent to process messages and generate responses. Agents can use tools, follow instructions, and maintain conversation context.
Input parameters
Number of completions to generate. Input tokens are billed once
Stop generation when this token (or any of these tokens if array) is detected
List of tools available for the agent to use during completion
Nucleus sampling parameter (0.0-1.0). Consider only tokens with cumulative probability >= top_p
Whether to stream partial responses. If true, returns server-sent events. Default false
ID of the agent to use for this completion. Obtain from listing or creating agents
List of messages forming the conversation. Must contain at least one message. Each message has a role ('system', 'user', 'assistant', 'tool') and content
Additional metadata to attach to the completion request
Maximum number of tokens to generate. The total of prompt + max_tokens cannot exceed model's context length
Prediction configuration for optimizing response times.
Prompt mode: 'reasoning' to enable reasoning mode with system prompt for reasoning models
Random seed for deterministic sampling. Same seed with same inputs produces same outputs
Sampling temperature (0.0-2.0). Higher values make output more random, lower values more deterministic
Controls tool selection: 'auto' (default), 'any', 'none', or specific tool object
Response format configuration.
Penalty for token presence (-2.0 to 2.0). Positive values encourage diverse vocabulary
Penalty for token frequency (-2.0 to 2.0). Positive values discourage repetition based on frequency
Whether to allow parallel tool calls. Default true
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_AUDIO_TRANSCRIPTIONTranscribe audio files to text using Mistral AI's Voxtral models. Use this action to convert speech in audio files to written text. Supports multiple input methods: file upload, file_id from previously uploaded files, or file_url for publicly accessible audio. The transcription supports 13 languages with automatic language detection, speaker diarization, and configurable timestamp granularities (segment or word level). Key features: - Multi-language support (English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, Dutch) - Speaker diarization to identify different speakers - Word and segment-level timestamps - Context biasing for domain-specific terminology - Supports common audio formats (mp3, wav, m4a, etc.) Note: Exactly one of file, file_id, or file_url must be provided. The action does not support streaming mode.
Input parameters
Audio file to transcribe. Supported formats include common audio formats (mp3, wav, m4a, etc.). Mutually exclusive with file_id and file_url - provide only one of these three options.
ID of the model to use for transcription. Use 'voxtral-mini-latest' for the latest version or 'voxtral-mini-2602' for a specific version. Supports 13 languages: English, Chinese, Hindi, Spanish, Arabic, French, Portuguese, Russian, German, Japanese, Korean, Italian, and Dutch.
Enable speaker diarization to identify different speakers in the audio. When enabled, the response will include speaker labels with timestamps.
ID of a previously uploaded file to transcribe. Obtain this from MISTRAL_AI_UPLOAD_FILE or MISTRAL_AI_LIST_FILES actions. Mutually exclusive with file and file_url - provide only one of these three options.
URL of an audio file to transcribe. The file must be publicly accessible. Mutually exclusive with file and file_id - provide only one of these three options.
Language code of the audio (e.g., 'en' for English, 'fr' for French, 'es' for Spanish, 'zh' for Chinese). Providing the language can improve transcription accuracy. If not provided, the language will be auto-detected.
Sampling temperature between 0 and 1. Higher values (e.g., 0.8) make output more random, lower values (e.g., 0.2) make it more focused and deterministic.
List of words or phrases to bias the transcription towards. Each item should be a single word or phrase without commas or whitespace within it. Use this to improve accuracy for domain-specific terminology.
Granularities of timestamps to include in the response. Options: 'segment' for segment-level timestamps, 'word' for word-level timestamps. Can include both for detailed timing information.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_CHAT_COMPLETIONGenerate conversational responses from Mistral AI models. Supports streaming, function calling, and various model parameters. Use when you need to create chat completions with Mistral AI models for conversation, question answering, or function calling scenarios.
Input parameters
Number of completions to return for each request. Input tokens are only billed once. Useful for generating multiple variations.
Stop generation if this token/string is detected. Can be a single string or list of strings.
ID of the model to use. Use the List Available Models API to see available models (e.g., 'mistral-tiny', 'mistral-small', 'mistral-medium', 'mistral-large-latest').
List of tools (functions) the model may call. Each tool should have 'type', 'function' with 'name', 'description', and 'parameters' (JSON schema).
Nucleus sampling probability mass. The model considers tokens with top_p probability mass. Default 1.0. We recommend altering this or temperature but not both.
Whether to stream back partial progress as server-sent events. When true, tokens are sent as they become available. Default false.
List of messages in the conversation. Each message has a 'role' (system/user/assistant/tool) and 'content'.
Optional metadata to include with the request for tracking or logging purposes.
Maximum number of tokens to generate in the completion. Prompt tokens plus max_tokens cannot exceed the model's context length.
Expected completion for optimizing response times.
Toggle between reasoning mode and no system prompt. When set to 'reasoning', the system prompt for reasoning models will be used.
Seed for random sampling. If set, different calls will generate deterministic results (same input = same output).
Whether to inject a safety prompt before all conversations to reduce harmful outputs. Default false.
Sampling temperature between 0.0 and 1.0. Higher values (e.g., 0.7) make output more random, lower values (e.g., 0.2) make it more focused and deterministic. Recommended range: 0.0-0.7.
Controls which tool is called by the model. 'none' means no tool calls, 'auto' lets model decide, 'any'/'required' means must call a tool. Or specify a tool: {"type": "function", "function": {"name": "my_function"}}. Default 'auto'.
Format specification for model output.
Penalizes word/phrase repetition regardless of frequency. Range: -2.0 to 2.0. Higher values encourage more diverse vocabulary. Default 0.0.
Penalizes word repetition based on frequency in the generated text. Range: -2.0 to 2.0. Higher values discourage repetition. Default 0.0.
Whether to enable parallel function calling during tool use. When enabled, the model can call multiple tools simultaneously. Default true.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_CHAT_MODERATIONTool to classify chat content for moderation purposes across 9 categories. Use when you need to detect harmful content, inappropriate messages, or policy violations in chat conversations.
Input parameters
Array of message objects to classify. Each message has a 'role' (user/assistant) and 'content' (string). The last user message will be classified for moderation.
Moderation model to use for classification. Use 'mistral-moderation-latest' for the most recent version.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_EMBEDDINGSTool to generate vector embeddings for input text using Mistral AI embedding models. Use when you need to convert text into numerical vectors for semantic search, similarity comparison, or RAG applications.
Input parameters
The text content to be embedded. Can be a single string or an array of strings for batch processing.
The ID of the model to be used for embedding (e.g., 'mistral-embed').
Output data type for embeddings.
Output encoding format for embeddings.
The dimension of the output embeddings when feature available. If not provided, a default output dimension will be used.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_FIM_COMPLETIONGenerate code completions using fill-in-the-middle functionality. Use when you need to complete code between a prefix and suffix, or continue code from a prompt. Ideal for code completion, function implementation, and context-aware code generation.
Input parameters
Stop generation if this token is detected. Can be a single string or an array of strings. When provided as array, generation stops if any of the tokens is detected.
ID of the model with FIM capability to use. Default: codestral-latest.
Nucleus sampling probability mass. The model considers tokens with top_p probability mass. For example, 0.1 means only tokens comprising the top 10% probability mass are considered. Default 1.0. Generally recommend altering this or temperature but not both.
The text/code to complete. This is the prefix that comes before the gap to be filled.
This parameter is not supported and will always be set to false. Streaming responses are not handled by this action.
Optional text/code that adds more context for the model. When given both prompt and suffix, the model fills what is between them. When suffix is not provided, the model simply executes completion starting with prompt.
Maximum number of tokens to generate in the completion. The token count of prompt plus max_tokens cannot exceed the model's context length.
Seed for random sampling. If set, different calls will generate deterministic results. Use for reproducible completions.
Sampling temperature between 0.0 and 1.0. Higher values like 0.7 make output more random, lower values like 0.2 make it more focused and deterministic. Recommended range: 0.0-0.7. Generally recommend altering this or top_p but not both.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_LIBRARYTool to create a new document library. Use when you need to group documents into a new library. Use after confirming authentication.
Input parameters
Name of the new document library
Optional description of the new document library
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_LIBRARY_SHARECreate or update sharing permissions for a library. Use to grant access to users, workspaces, or organizations. Specify the access level (Viewer or Editor) and the entity to share with. This is a beta endpoint.
Input parameters
Access level to grant: 'Viewer' for read-only access or 'Editor' for read and write access
Optional organization ID to associate with the share (UUID format)
Unique identifier of the library to share (UUID format)
The type of entity to share the library with: 'User' for individual users, 'Workspace' for team workspaces, or 'Org' for entire organizations
The UUID of the entity (user, workspace, or organization) to share the library with
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_MODERATIONTool to classify text content for moderation purposes across 9 categories. Use when you need to detect harmful content, inappropriate text, or policy violations in raw text inputs.
Input parameters
Text to classify for moderation. Can be a single string or an array of strings for batch processing.
Moderation model to use for classification. Use 'mistral-moderation-latest' for the most recent version.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_OCRExtract text and structured data from images and documents using Mistral AI's OCR capabilities. Supports PDFs, images, tables, headers, footers, and custom structured extraction. Use when you need to digitize documents, extract invoice data, parse forms, or convert scanned documents to text.
Input parameters
Optional custom identifier for this OCR request.
Model to use for OCR processing. Use 'mistral-ocr-latest' for the latest version or specific version like 'mistral-ocr-2512'.
Specific pages to process (0-indexed). Can be single numbers, ranges, or lists. If not specified, all pages are processed.
Document to run OCR on. Can be an image URL, document URL, or file ID of a previously uploaded file.
Maximum number of images to extract from the document.
Format for extracted tables.
Whether to extract footer content from the document. Default false.
Whether to extract header content from the document. Default false.
Minimum height and width (in pixels) for images to extract. Smaller images are ignored.
Whether to include base64-encoded image data in the response.
Response format specification for structured output.
Response format specification for structured output.
Optional prompt to guide the model in extracting structured output from the entire document. Requires document_annotation_format to be provided.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_CREATE_OR_UPDATE_AGENT_ALIASTool to create or update an agent version alias. Use when you need to assign a version alias (like 'production' or 'staging') to a specific agent version.
Input parameters
Name of the version alias (e.g., 'production', 'staging', 'latest').
Agent version number to assign to this alias. Must be a non-negative integer.
Unique identifier of the agent (UUID format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_AGENTPermanently deletes an agent by its ID (Beta feature). Use this tool when you need to remove an agent that is no longer needed. This operation is irreversible - the agent will be permanently removed from the system.
Input parameters
The unique identifier of the agent to delete. This should be the agent ID returned from previous agent operations (e.g., ag_019c5ecefcc37282b0fff41b4b3a8f5d).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_CONVERSATIONTool to delete a conversation by its ID (Beta). Use when you need to permanently remove a conversation. This is a beta feature.
Input parameters
ID of the conversation to delete. Must be a valid conversation ID.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_FILEDelete a file by its ID from Mistral AI. Permanently removes the file and its metadata. Use List Files action first to obtain valid file IDs.
Input parameters
UUID of the file to delete. Obtain file IDs from the List Files action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_LIBRARYPermanently deletes a library and all of its documents from Mistral AI. Use this tool when you need to remove an entire library including all its documents. This operation is irreversible - the library and all its documents will be permanently removed. Returns the deleted library details on success. Common errors: - 404: Library not found (already deleted or invalid library_id) - 422: Invalid UUID format for library_id
Input parameters
The unique UUID identifier of the library to delete. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_LIBRARY_DOCUMENTPermanently deletes a document from a Mistral AI library. Use this tool when you need to remove a specific document from a library. Both library_id and document_id must be valid UUIDs. This operation is irreversible - the document will be permanently removed. Returns an empty response on success (HTTP 204). Common errors: - 404: Document not found (already deleted or invalid document_id) - 422: Invalid UUID format for library_id or document_id
Input parameters
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
The unique UUID identifier of the document to delete. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DELETE_LIBRARY_SHARERemove sharing permissions for a library from a user, workspace, or organization. Use when you need to revoke access to a library that was previously shared. This is a beta feature.
Input parameters
Optional organization ID for scoping the operation.
The unique UUID identifier of the library to remove sharing permissions from. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
The type of entity (User, Workspace, or Org) to revoke access from.
The UUID of the entity (user, workspace or organization) to revoke access from. Must be a valid UUID format.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_DOWNLOAD_FILEDownload the content of a previously uploaded file from Mistral AI. Returns the raw binary content of the file. Use this when you need to retrieve file data for processing, such as training data files (.jsonl) for fine-tuning. Requires a valid file_id which can be obtained from the list_files or upload_file actions.
Input parameters
The unique identifier (UUID) of the file to download. Obtain this from the list_files or upload_file actions.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_AGENTTool to retrieve details of a specific Mistral AI agent by its ID. Returns comprehensive agent information including model, instructions, tools, and configuration. Use when you need to inspect or verify an agent's settings.
Input parameters
UUID of the agent to retrieve. Obtain agent IDs from the List Agents action.
Specific version of the agent to retrieve. If not provided, the latest version is returned.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_AGENT_VERSIONRetrieve a specific version of an agent (Beta). Use when you need to get details about a particular agent version, including its configuration, tools, and metadata.
Input parameters
Version number of the agent to retrieve (e.g., '0', '1', '2').
UUID of the agent to retrieve. Obtain agent IDs from the List Agents action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_CONVERSATIONTool to retrieve details of a specific conversation. Use when you need to fetch conversation metadata including timestamps, configuration, and associated model or agent information.
Input parameters
ID of the conversation from which we are fetching metadata.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_CONVERSATION_HISTORYRetrieve the full history of a conversation in Mistral AI. Returns all entries including messages, tool calls, function results, and agent handoffs. Use this to review conversation context or export conversation data. Note: This is a beta endpoint.
Input parameters
ID of the conversation from which we are fetching entries.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_CONVERSATION_MESSAGESRetrieve all messages from a Mistral AI conversation. Use when you need to fetch the complete message history for a specific conversation.
Input parameters
ID of the conversation from which to fetch messages. This is a unique identifier for the conversation in Mistral AI's system.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_DOCUMENT_EXTRACTED_TEXT_URLRetrieve a signed URL to download the extracted text from a document in a Mistral AI library. This is a beta endpoint. Note: Only documents that undergo OCR processing (such as PDFs) will have extracted text available; plain text files that don't require OCR will return a 404 error.
Input parameters
The unique UUID identifier of the library containing the document. Use MISTRAL_AI_LIST_LIBRARIES to get available library IDs.
The unique UUID identifier of the document. Use MISTRAL_AI_LIST_LIBRARY_DOCUMENTS to get document IDs. Note: Only documents that undergo OCR processing (e.g., PDFs) will have extracted text available.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_DOCUMENT_SIGNED_URLGet a signed URL to download a document from a Mistral AI library. Returns a temporary URL that provides direct access to download the document content. Use this when you need to retrieve document files from a library. The signed URL is typically valid for 30 minutes.
Input parameters
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
The unique UUID identifier of the document to retrieve the signed URL for. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_DOCUMENT_STATUSRetrieve the processing status of a document in a Mistral AI library. Use this to check if a document has finished processing after upload. Returns the document ID and its current processing status.
Input parameters
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_DOCUMENT_TEXT_CONTENTRetrieve the extracted text content of a specific document from a Mistral AI library (Beta). Returns the full text content extracted from the document. Use the List Libraries action first to obtain valid library IDs, then use List Library Documents to get document IDs.
Input parameters
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action or from the document URL in Le Chat.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_FILE_SIGNED_URLGet a time-limited signed URL for downloading a file from Mistral AI. Use when you need a temporary download link that can be shared or used externally. The URL expires after the specified number of hours (default 24).
Input parameters
Number of hours before the URL becomes invalid. Defaults to 24 hours if not specified.
UUID of the file to get signed URL for. Obtain file IDs from the List Files action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_FINE_TUNING_JOBSList fine-tuning jobs with optional filtering and pagination. Use this tool to retrieve all fine-tuning jobs for your organization. Supports filtering by model, status, creation time, and W&B integration. Results are paginated; use 'page' and 'page_size' to navigate large result sets.
Input parameters
Page number of results to return (0-indexed). Default is 0.
Filter by the base model name used for fine-tuning. When set, only jobs using this model are returned.
Filter by the current job status. Valid values: QUEUED, STARTED, VALIDATING, VALIDATED, RUNNING, FAILED_VALIDATION, FAILED, SUCCESS, CANCELLED, CANCELLATION_REQUESTED.
Filter by the model suffix used when creating the fine-tuned model.
Number of fine-tuning jobs to return per page (1-1000). Default is 100.
Filter by the Weights and Biases run name.
Filter to return only jobs created after this date/time (ISO 8601 format).
When set to true, only return jobs created by the API caller. Default is false.
Filter by the Weights and Biases project name.
Filter to return only jobs created before this date/time (ISO 8601 format).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_LIBRARYRetrieve detailed information about a specific library. Returns complete library metadata including name, description, document counts, size, timestamps, and ownership details. Use List Libraries action first to obtain valid library IDs.
Input parameters
UUID of the library to retrieve. Obtain library IDs from the List Libraries action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_LIBRARY_DOCUMENTRetrieve metadata for a specific document in a Mistral AI library. Returns detailed information including processing status, size, summary, token counts, and timestamps. Use this to check document status after upload or to retrieve details for a known document.
Input parameters
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_GET_MODELTool to retrieve detailed information about a specific Mistral AI model by its ID. Returns model metadata including capabilities, context length, and ownership. Use when you need to inspect model specifications before using it.
Input parameters
The ID of the model to retrieve. Use model identifiers like 'mistral-small-latest', 'mistral-large-latest', or fine-tuned model IDs in format 'ft:open-mistral-7b:587a6b29:20240514:7e773925'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_AGENT_ALIASESRetrieve all aliases for an agent version. Use to view and manage version aliases for an agent. Note: This is a beta endpoint.
Input parameters
Unique identifier of the agent. Obtain agent IDs from the List Agents action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_AGENTSTool to list all configured agents (Beta). Use when you need to retrieve a list of agents available in your organization.
Input parameters
Filter agents by ID.
Filter agents by name.
Page number (0-indexed) for pagination. Default is 0.
Filter agents by source.
Filter agents by metadata.
Number of agents to return per page. Default is 20.
Filter agents by deployment chat setting.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_AGENT_VERSIONSList all versions of a specific agent. Use when you need to view the version history of an agent. Note: This is a beta endpoint.
Input parameters
Page number for pagination (0-indexed). Default is 0.
Unique identifier of the agent to retrieve versions for.
Number of versions to return per page. Default is 20.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_BATCH_JOBSTool to retrieve a list of all batch jobs with optional filtering and pagination. Use when you need to view or manage batch processing jobs.
Input parameters
Page number of results to return (0-indexed). Default is 0.
Filter by the model name used for batch processing. When set, only jobs using this model are returned.
Filter by the current batch job status. Valid values include: QUEUED, RUNNING, SUCCESS, FAILED, CANCELLED.
Filter by agent ID. When set, only batch jobs associated with this agent are returned.
Filter by metadata string. When set, only batch jobs with matching metadata are returned.
Number of batch jobs to return per page (1-1000). Default is 100.
Filter to return only jobs created after this date/time (ISO 8601 format).
When set to true, only return batch jobs created by the API caller. Default is false.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_CONVERSATIONSList all created conversations (Beta). Use to retrieve conversation history or manage existing conversations. Supports pagination and metadata filtering.
Input parameters
Page number of results to return (0-indexed). Default is 0.
Filter conversations by metadata. Exact format depends on your metadata structure.
Number of conversations to return per page (1-1000). Default is 100.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_FILESTool to list all files available to the user. Use when you need to view or manage uploaded files, supports pagination.
Input parameters
Pagination cursor: file ID to start after. Use to retrieve the next page of results.
Maximum number of files to return, must be >=1. Default is server-side limit.
Order to list files: 'asc' for ascending or 'desc' for descending. Default 'desc'.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_LIBRARIESList all document libraries accessible to your organization. Returns library metadata including id, name, description, document counts, and timestamps. Use to discover available libraries before listing or uploading documents. Note: This is a beta endpoint.
Input parameters
(Beta) Maximum number of libraries to return per page. May not be honored in beta.
(Beta) Token for fetching the next page of results. May not be honored in beta.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_LIBRARY_DOCUMENTSList all documents in a Mistral AI document library. Returns document metadata including name, processing status, size, summary, and timestamps. Use the List Libraries action first to obtain valid library IDs. Supports pagination for large libraries.
Input parameters
Page number to retrieve (0-indexed). Use with page_size for pagination.
Number of documents per page. Defaults to 100 if not specified.
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_LIBRARY_SHARESList all sharing permissions for a document library. Returns details about who has access to the library, including role, share type, and user/organization identifiers. Use the List Libraries action first to obtain valid library IDs. Note: This is a beta endpoint.
Input parameters
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_LIST_MODELSTool to retrieve all available Mistral AI models including base models and fine-tuned models. Use when you need to see what models are available for chat completions, embeddings, or fine-tuning.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_REPROCESS_DOCUMENTReprocess a document in a Mistral AI library (Beta). Use when you need to trigger reprocessing of a document, such as after updating library settings or to refresh document embeddings. Both library_id and document_id must be valid UUIDs. Returns an empty response on success (HTTP 204).
Input parameters
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
The unique UUID identifier of the document to reprocess. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_RESTART_CONVERSATIONTool to restart a conversation from a specific point (Beta). Use when you need to branch a conversation or replay it from a particular message. Creates a new conversation starting from the specified entry.
Input parameters
Whether to persist the conversation results to the server. Defaults to true
New input to append when restarting the conversation. Can be a string (simple text input) or an array of entry objects (MessageInputEntry, MessageOutputEntry, FunctionResultEntry, etc.)
Enable response streaming for real-time output. Defaults to false
Additional metadata to associate with the restarted conversation
Version of the agent to use when restarting the conversation
ID of the entry from which to restart the conversation. The conversation will be recreated from this point
White-listed arguments from the completion API to configure the response generation (e.g., temperature, max_tokens)
ID of the original conversation which is being restarted
Handoff execution mode for agent handoffs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_RETRIEVE_FILERetrieve metadata of a file uploaded to Mistral AI. Returns file details including size, filename, purpose, and creation time. Use List Files action first to obtain valid file IDs.
Input parameters
UUID of the file to retrieve. Obtain file IDs from the List Files action.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_START_CONVERSATIONTool to start a new conversation with a Mistral AI agent or base model. Use when initiating a conversational interaction that requires context tracking. Either 'model' or 'agent_id' must be provided. Returns a conversation_id for continuing the conversation.
Input parameters
Name for the conversation to help identify it later.
Specifies which base model to use. Either 'model' or 'agent_id' must be set. Examples: 'mistral-small-latest', 'mistral-large-latest', 'mistral-medium-latest'.
Whether to persist the conversation history. Set to false to prevent cloud storage. Default is true.
Available tools for the conversation (FunctionTool, WebSearchTool, CodeInterpreterTool, etc.). Array of tool definition objects.
The initial message(s) to append to the conversation. Can be a simple string or an array of entry objects with 'content' and 'role' fields.
Set true for streaming responses as Server-Sent Events. Default is false (returns complete JSON response).
ID of an agent to use instead of a base model. Either 'model' or 'agent_id' must be set.
Custom key-value metadata to attach to the conversation for tracking or organization.
Description of the conversation purpose or context.
System instructions to guide the conversation behavior and style.
Specific agent version to use. Only applicable when 'agent_id' is specified.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPDATE_AGENTTool to update an existing agent's configuration. Use when you need to modify an agent's name, description, model, instructions, tools, or other settings.
Input parameters
Updated name for the agent
Updated model to use for the agent (e.g., 'mistral-large-latest', 'mistral-small-latest')
Updated list of tools available to the model during conversation
The unique identifier of the agent to update
Updated list of handoff configurations
Updated custom metadata to associate with the agent
Updated description of the agent's purpose
Updated instruction prompt the model will follow during the conversation
White-listed arguments from the completion API.
Updated flag indicating if agent is deployed for chat
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPDATE_AGENT_VERSIONTool to update the current version of an agent (Beta). Use when you need to switch an agent to a different version from its available versions.
Input parameters
Version number to set as the current version. Must be a non-negative integer from the agent's available versions list.
Unique identifier of the agent to update (e.g., 'ag_019c5ecef27c7721a09ec60a67fceee5')
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPDATE_LIBRARYTool to update an existing document library's properties. Use when you need to modify a library's name or description. Note: This is a beta endpoint.
Input parameters
New name for the library. If not provided, the current name is retained.
Unique identifier (UUID) of the library to update
New description for the library. If not provided, the current description is retained.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPDATE_LIBRARY_DOCUMENTUpdate the metadata of a document in a Mistral AI library. Use this to modify a document's name or add/update custom attributes without re-uploading the file content. This is a beta endpoint.
Input parameters
New name for the document. If provided, this will replace the current document name.
Custom attributes to attach to the document as key-value pairs. Can be used to store metadata such as category, priority, tags, or any other relevant information.
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
The unique UUID identifier of the document to update. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPLOAD_FILEUpload a file to Mistral AI for use in fine-tuning, batch processing, or OCR. Use this tool to: - Upload .jsonl files for fine-tuning models - Upload files for batch processing requests - Upload documents for OCR processing Maximum file size: 512 MB. For fine-tuning, only .jsonl files are supported.
Input parameters
File to upload to Mistral AI.
Purpose for the uploaded file.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
MISTRAL_AI_UPLOAD_LIBRARY_DOCUMENTUpload a document to a Mistral AI library for use with RAG-enabled agents. Use this action to add documents to a library that can be accessed by Mistral AI agents. The uploaded document will be processed and indexed for retrieval-augmented generation. Prerequisites: - First obtain a valid library_id using MISTRAL_AI_LIST_LIBRARIES or MISTRAL_AI_CREATE_LIBRARY. - Supported file formats include PDF, TXT, DOC, DOCX, and other common document types. - Maximum file size is 100 MB per document.
Input parameters
File to upload. Supported formats include PDF, TXT, DOC, DOCX, and other common document types.
Unique identifier (UUID) of the library where the document will be uploaded. Use MISTRAL_AI_LIST_LIBRARIES to get available library IDs.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 75 agents privately built on Nagent that already use Mistral AI.
Build on Nagent
Connect Mistral AI to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Mistral AI, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Mistral AI is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Mistral AI is connected, you configure its 54 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Mistral AI steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Mistral AI event fires, the agent kicks off automatically.
Every Mistral AI action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Mistral AI ships with 54 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Mistral AI together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Mistral AI-based workflows tailored to your business.