Skip to main content
Mistral AI logo
  • Category: artificial intelligence
  • Auth: API_KEY
  • Composio-managed OAuth available? N/A
  • Tools: 105
  • Triggers: 0
  • Slug: MISTRAL_AI
  • Version: 20261101_00
  • Instant: Supported on the latest version. Support varies by tool.

Tools

Slug: 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

boolean
Whether to persist the conversation results to the server. Defaults to true
string
required
New input to append to the conversation. Can be a string (simple text input) or an array of entry objects (MessageInputEntry, MessageOutputEntry, FunctionResultEntry, etc.)
object
White-listed arguments from the completion API to configure the response generation (e.g., temperature, max_tokens)
string
required
ID of the conversation to which entries will be appended
string ("client" | "server")
Handoff execution mode for agent handoffs.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_ARCHIVE_FINE_TUNED_MODELArchive a fine-tuned model so it is unavailable until restored.

Input Parameters

string
required
Fine-tuned model identifier.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_COUNT_CHAT_COMPLETION_FIELD_OPTIONSCount values of a chat completion field after optional filtering.

Input Parameters

string
required
Chat completion field whose values to count. Call List Chat Completion Fields first to discover valid field names.
object
Optional filter object with required filters. Use a condition with field, op, and value, or nest conditions in AND/OR arrays. Example: {"filters":{"field":"model","op":"eq","value":"mistral-large"}}. Operators: lt, lte, gt, gte, startswith, istartswith, endswith, iendswith, contains, icontains, matches, notcontains, inotcontains, eq, neq, isnull, includes, excludes, len_eq.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Name of the agent
string
required
Model ID to use for the agent (e.g., ‘mistral-large-latest’, ‘mistral-small-latest’)
array
List of tools available to the agent. Can include function tools, web search, code interpreter, image generation, or document library tools
array
Optional handoff configuration for agent-to-agent transfers
object
Optional metadata to attach to the agent
string
Optional description of the agent’s purpose and capabilities
string
System instructions that guide the agent’s behavior during conversations
object
White-listed arguments from the completion API.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
Number of completions to generate. Input tokens are billed once
string
Stop generation when this token (or any of these tokens if array) is detected
array
List of tools available for the agent to use during completion
number
Nucleus sampling parameter (0.0-1.0). Consider only tokens with cumulative probability >= top_p
boolean
Whether to stream partial responses. If true, returns server-sent events. Default false
string
required
ID of the agent to use for this completion. Obtain from listing or creating agents
array
required
List of messages forming the conversation. Must contain at least one message. Each message has a role (‘system’, ‘user’, ‘assistant’, ‘tool’) and content
object
Additional metadata to attach to the completion request
integer
Maximum number of tokens to generate. The total of prompt + max_tokens cannot exceed model’s context length
object
Prediction configuration for optimizing response times.
string
Prompt mode: ‘reasoning’ to enable reasoning mode with system prompt for reasoning models
integer
Random seed for deterministic sampling. Same seed with same inputs produces same outputs
number
Sampling temperature (0.0-2.0). Higher values make output more random, lower values more deterministic
string
Controls tool selection: ‘auto’ (default), ‘any’, ‘none’, or specific tool object
object
Response format configuration.
number
Penalty for token presence (-2.0 to 2.0). Positive values encourage diverse vocabulary
number
Penalty for token frequency (-2.0 to 2.0). Positive values discourage repetition based on frequency
boolean
Whether to allow parallel tool calls. Default true

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

object
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.
string
required
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.
boolean
Enable speaker diarization to identify different speakers in the audio. When enabled, the response will include speaker labels with timestamps.
string
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.
string
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.
string
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.
number
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.
array
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.
array
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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_CREATE_BATCH_JOBCreate and queue a Mistral batch inference job.

Input Parameters

string
Model used for batch inference.
string
Deprecated agent identifier.
string ("/v1/chat/completions" | "/v1/embeddings" | "/v1/fim/completions" | "/v1/moderations" | "/v1/chat/moderations" | "/v1/ocr" | "/v1/classifications" | "/v1/chat/classifications" | "/v1/conversations" | "/v1/audio/transcriptions")
required
API endpoint used for batch inference.
object
Caller metadata with 1-32 character keys and 1-512 character values.
array
Inline batch requests.
array
Uploaded JSONL file UUIDs containing batch requests.
integer
Batch timeout in hours.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_CREATE_CHAT_COMPLETIONGenerate conversational responses from Mistral AI models with function calling and various model parameters. Responses are non-streaming.

Input Parameters

integer
Number of completions to return for each request. Input tokens are only billed once. Useful for generating multiple variations.
string
Stop generation if this token/string is detected. Can be a single string or list of strings.
string
required
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’).
array
List of tools (functions) the model may call. Each tool should have ‘type’, ‘function’ with ‘name’, ‘description’, and ‘parameters’ (JSON schema).
number
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.
boolean
Whether to stream back partial progress as server-sent events. When true, tokens are sent as they become available. Default false.
array
required
List of messages in the conversation. Each message has a ‘role’ (system/user/assistant/tool) and ‘content’.
object
Optional metadata to include with the request for tracking or logging purposes.
integer
Maximum number of tokens to generate in the completion. Prompt tokens plus max_tokens cannot exceed the model’s context length.
object
Expected completion for optimizing response times.
string
Toggle between reasoning mode and no system prompt. When set to ‘reasoning’, the system prompt for reasoning models will be used.
integer
Seed for random sampling. If set, different calls will generate deterministic results (same input = same output).
boolean
Whether to inject a safety prompt before all conversations to reduce harmful outputs. Default false.
number
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.
string
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’.
object
Format specification for model output.
number
Penalizes word/phrase repetition regardless of frequency. Range: -2.0 to 2.0. Higher values encourage more diverse vocabulary. Default 0.0.
number
Penalizes word repetition based on frequency in the generated text. Range: -2.0 to 2.0. Higher values discourage repetition. Default 0.0.
boolean
Whether to enable parallel function calling during tool use. When enabled, the model can call multiple tools simultaneously. Default true.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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
required
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.
string
Moderation model to use for classification. Use ‘mistral-moderation-latest’ for the most recent version.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The text content to be embedded. Can be a single string or an array of strings for batch processing.
string
required
The ID of the model to be used for embedding (e.g., ‘mistral-embed’).
string ("float" | "int8" | "uint8" | "binary" | "ubinary")
Output data type for embeddings.
string ("float" | "base64")
Output encoding format for embeddings.
integer
The dimension of the output embeddings when feature available. If not provided, a default output dimension will be used.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
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.
string
ID of the model with FIM capability to use. Default: codestral-latest.
number
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.
string
required
The text/code to complete. This is the prefix that comes before the gap to be filled.
boolean
This parameter is not supported and will always be set to false. Streaming responses are not handled by this action.
string
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.
integer
Maximum number of tokens to generate in the completion. The token count of prompt plus max_tokens cannot exceed the model’s context length.
integer
Seed for random sampling. If set, different calls will generate deterministic results. Use for reproducible completions.
number
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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Name of the new document library
string
Optional description of the new document library

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string ("Viewer" | "Editor")
required
Access level to grant: ‘Viewer’ for read-only access or ‘Editor’ for read and write access
string
Optional organization ID to associate with the share (UUID format)
string
required
Unique identifier of the library to share (UUID format)
string ("User" | "Workspace" | "Org")
required
The type of entity to share the library with: ‘User’ for individual users, ‘Workspace’ for team workspaces, or ‘Org’ for entire organizations
string
required
The UUID of the entity (user, workspace, or organization) to share the library with

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Text to classify for moderation. Can be a single string or an array of strings for batch processing.
string
Moderation model to use for classification. Use ‘mistral-moderation-latest’ for the most recent version.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_CREATE_OCRExtract text and structured data from images and documents using Mistral AI OCR, including tables, headers, footers, and custom structured extraction. Managed OCR requires mistral-ocr-4-1 and direct URLs, limits page selections to 1–10 distinct nonnegative indexes, and does not support annotation add-ons.Instant: Supported on the latest version.Instant pricing: $0.004 per standard OCR 4.1 page

Input Parameters

string
Optional custom identifier for this OCR request.
string
required
Model to use for OCR processing. Use ‘mistral-ocr-latest’ for the latest version or specific version like ‘mistral-ocr-2512’.
array
Specific pages to process (0-indexed). Can be single numbers, ranges, or lists. If not specified, all pages are processed.
string
required
Document to run OCR on. Can be an image URL, document URL, or file ID of a previously uploaded file.
integer
Maximum number of images to extract from the document.
string ("markdown" | "html")
Format for extracted tables.
Whether to extract footer content from the document. Default false.
boolean
Whether to extract header content from the document. Default false.
integer
Minimum height and width (in pixels) for images to extract. Smaller images are ignored.
boolean
Whether to include base64-encoded image data in the response.
object
Response format specification for structured output.
object
Response format specification for structured output.
string
Optional prompt to guide the model in extracting structured output from the entire document. Requires document_annotation_format to be provided.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Name of the version alias (e.g., ‘production’, ‘staging’, ‘latest’).
integer
required
Agent version number to assign to this alias. Must be a non-negative integer.
string
required
Unique identifier of the agent (UUID format).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_CREATE_SPEECHGenerate JSON-encoded speech audio from text without streaming.

Input Parameters

string
required
Text to generate speech from.
string
required
Speech model identifier, such as voxtral-mini-tts-latest.
string
Preset or custom voice used to generate speech.
string
Base64-encoded reference audio for zero-shot voice cloning.
string ("pcm" | "wav" | "mp3" | "flac" | "opus")
Output audio format.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique identifier of the agent to delete. This should be the agent ID returned from previous agent operations (e.g., ag_019c5ecefcc37282b0fff41b4b3a8f5d).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
ID of the conversation to delete. Must be a valid conversation ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
UUID of the file to delete. Obtain file IDs from the List Files action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_DELETE_LIBRARYPermanently delete a library and its documents from Mistral AI. The response may contain deleted library details, or only the library ID when no details are returned.

Input Parameters

string
required
The unique UUID identifier of the library to delete. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
string
required
The unique UUID identifier of the document to delete. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
Optional organization ID for scoping the operation.
string
required
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).
string ("User" | "Workspace" | "Org")
required
The type of entity (User, Workspace, or Org) to revoke access from.
string
required
The UUID of the entity (user, workspace or organization) to revoke access from. Must be a valid UUID format.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_DOWNLOAD_FILEDownload the content of a previously uploaded Mistral AI file by ID. Returns the file as a downloadable object for processing, such as training data for fine-tuning.

Input Parameters

string
required
The unique identifier (UUID) of the file to download. Obtain this from the list_files or upload_file actions.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
UUID of the agent to retrieve. Obtain agent IDs from the List Agents action.
string
Specific version of the agent to retrieve. If not provided, the latest version is returned.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Version number of the agent to retrieve (e.g., ‘0’, ‘1’, ‘2’).
string
required
UUID of the agent to retrieve. Obtain agent IDs from the List Agents action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_BATCH_JOBGet details and optionally inline results for a batch job.

Input Parameters

boolean
Return job results inline in the outputs field.
string
required
Batch job UUID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CAMPAIGNRetrieve an observability campaign by its UUID.

Input Parameters

string
required
UUID of the campaign to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CAMPAIGN_STATUSReturn the execution status of an observability campaign.

Input Parameters

string
required
UUID of the campaign whose status should be returned.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CHAT_COMPLETION_EVENTRetrieve one observability chat completion event by UUID.

Input Parameters

string
required
UUID of the chat completion event to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CHAT_COMPLETION_FIELD_OPTIONSGet available values for a chat completion field and filter operator.

Input Parameters

string ("lt" | "lte" | "gt" | "gte" | "startswith" | "istartswith" | "endswith" | "iendswith" | "contains" | "icontains" | "matches" | "notcontains" | "inotcontains" | "eq" | "neq" | "isnull" | "includes" | "excludes" | "len_eq")
required
Operator for which options are requested.
string
required
Chat completion field whose options to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CONNECTORGet a connector by ID or name without requesting customer data or secrets.

Input Parameters

string
required
Connector UUID or name.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_CONNECTOR_AUTHENTICATION_METHODSGet a connector’s public authentication methods and required headers.

Input Parameters

string
required
Connector UUID or name.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
ID of the conversation from which we are fetching metadata.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
ID of the conversation from which we are fetching entries.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
ID of the conversation from which to fetch messages. This is a unique identifier for the conversation in Mistral AI’s system.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_DATASETRetrieve an observability dataset by its UUID.

Input Parameters

string
required
UUID of the dataset to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_DATASET_IMPORT_TASKRetrieve the status and progress of one dataset import task.

Input Parameters

string
required
UUID of the import task to retrieve.
string
required
UUID of the dataset associated with the import task.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_DATASET_RECORDRetrieve a conversation record from an observability dataset.

Input Parameters

string
required
UUID of the dataset record to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique UUID identifier of the library containing the document. Use MISTRAL_AI_LIST_LIBRARIES to get available library IDs.
string
required
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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
string
required
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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
string
required
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
string
required
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action or from the document URL in Le Chat.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
Number of hours before the URL becomes invalid. Defaults to 24 hours if not specified.
string
required
UUID of the file to get signed URL for. Obtain file IDs from the List Files action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
Page number of results to return (0-indexed). Default is 0.
string
Filter by the base model name used for fine-tuning. When set, only jobs using this model are returned.
string
Filter by the current job status. Valid values: QUEUED, STARTED, VALIDATING, VALIDATED, RUNNING, FAILED_VALIDATION, FAILED, SUCCESS, CANCELLED, CANCELLATION_REQUESTED.
string
Filter by the model suffix used when creating the fine-tuned model.
integer
Number of fine-tuning jobs to return per page (1-1000). Default is 100.
string
Filter by the Weights and Biases run name.
string
Filter to return only jobs created after this date/time (ISO 8601 format).
boolean
When set to true, only return jobs created by the API caller. Default is false.
string
Filter by the Weights and Biases project name.
string
Filter to return only jobs created before this date/time (ISO 8601 format).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_JUDGERetrieve a saved observability judge by UUID.

Input Parameters

string
required
UUID of the saved judge to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
UUID of the library to retrieve. Obtain library IDs from the List Libraries action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.
string
required
The unique identifier (UUID) for the document. Obtain this from the List Library Documents action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_SIMILAR_CHAT_COMPLETION_EVENTSRetrieve observability events similar to a specified event.

Input Parameters

string
required
UUID of the event for which to find similar events.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_VOICEGet saved voice metadata without sample audio.

Input Parameters

string
required
Voice identifier.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_VOICE_SAMPLEDownload a saved voice’s sample as a WAV audio file.

Input Parameters

string
required
Voice identifier.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOWRetrieve a workflow definition and its active-worker status by name or ID.

Input Parameters

string
required
Workflow name or ID to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_DEPLOYMENTRetrieve a workflow deployment and its registered workers.

Input Parameters

string
required
Name of the deployment to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_EXECUTIONRetrieve the current state and result of a workflow execution.

Input Parameters

string
required
ID of the workflow execution to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_EXECUTION_HISTORYRetrieve the event history for a workflow execution.

Input Parameters

string
required
ID of the workflow execution whose history to retrieve.
boolean
Whether to decode payloads in the returned history.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_EXECUTION_OTEL_TRACERetrieve raw OpenTelemetry trace data for a workflow execution.

Input Parameters

string
required
ID of the workflow execution whose OpenTelemetry trace to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_EXECUTION_TRACE_EVENTSRetrieve trace events for a workflow execution.

Input Parameters

string
required
ID of the workflow execution whose trace events to retrieve.
boolean
Whether to merge events that share the same ID.
boolean
Whether to include internal trace events.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_EXECUTION_TRACE_SUMMARYRetrieve a hierarchical trace summary for a workflow execution.

Input Parameters

string
required
ID of the workflow execution whose trace summary to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_METRICSRetrieve aggregate execution, error, latency, and retry metrics for a workflow.

Input Parameters

string
Only include workflows started before this ISO 8601 time.
string
Only include workflows started after this ISO 8601 time.
string
required
Name of the workflow whose metrics to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_REGISTRATIONRetrieve one workflow registration and its worker availability.

Input Parameters

boolean
Whether to include the workflow definition.
boolean
Whether to include shared workflow registrations.
string
required
UUID of the workflow registration to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_RUNRetrieve a workflow run’s status, timing, execution IDs, and result.

Input Parameters

string
required
UUID of the workflow run to retrieve.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_GET_WORKFLOW_RUN_HISTORYRetrieve the event history for a workflow run.

Input Parameters

string
required
UUID of the workflow run whose history to retrieve.
boolean
Whether to decode payloads in the returned history.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_JUDGE_CHAT_COMPLETION_EVENTEvaluate one chat completion event with an inline judge definition.

Input Parameters

string
required
UUID of the chat completion event to evaluate.
object
required
Inline judge with name, description, model_name, instructions, tools, and output. Output is CLASSIFICATION with value/description options or REGRESSION with numeric min/max descriptions. Example: {"name":"Helpfulness judge","description":"Checks helpfulness","model_name":"mistral-small-latest","output":{"type":"CLASSIFICATION","options":[{"value":"helpful","description":"The response is helpful"}]},"instructions":"Classify the response","tools":[]}.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_JUDGE_CONVERSATIONRun a saved observability judge against a supplied conversation.

Input Parameters

string
required
UUID of the saved judge to run.
array
required
Conversation messages to evaluate, for example [{"role": "user", "content": "Hello"}]. Message objects may include additional fields accepted by the judge.
object
Optional properties supplied to the judge.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_JUDGE_DATASET_RECORDEvaluate one dataset record with a supplied non-durable judge definition.

Input Parameters

object
required
Non-durable judge with name, description, model_name, instructions, tools, and output. Output is CLASSIFICATION with value/description options or REGRESSION with numeric min/max descriptions. Example: {"name":"Quality judge","description":"Scores quality","model_name":"mistral-small-latest","output":{"type":"REGRESSION","min":0,"min_description":"Poor","max":1,"max_description":"Excellent"},"instructions":"Score response quality","tools":[]}.
string
required
UUID of the dataset record to evaluate.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_AGENT_ALIASESList version aliases for a specified agent (Beta), including the version associated with each alias.

Input Parameters

string
required
Unique identifier of the agent. Obtain agent IDs from the List Agents action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_AGENTSList configured agents available in your organization (Beta), with optional filters and pagination.

Input Parameters

string
Filter agents by ID.
string
Filter agents by name.
integer
Page number (0-indexed) for pagination. Default is 0.
string
Filter agents by source.
string
Filter agents by metadata.
integer
Number of agents to return per page. Default is 20.
boolean
Filter agents by deployment chat setting.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_AGENT_VERSIONSList versions of a specific agent (Beta) to view its version history. Results are paginated.

Input Parameters

integer
Page number for pagination (0-indexed). Default is 0.
string
required
Unique identifier of the agent to retrieve versions for.
integer
Number of versions to return per page. Default is 20.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
Page number of results to return (0-indexed). Default is 0.
string
Filter by the model name used for batch processing. When set, only jobs using this model are returned.
string
Filter by the current batch job status. Valid values include: QUEUED, RUNNING, SUCCESS, FAILED, CANCELLED.
string
Filter by agent ID. When set, only batch jobs associated with this agent are returned.
string
Filter by metadata string. When set, only batch jobs with matching metadata are returned.
integer
Number of batch jobs to return per page (1-1000). Default is 100.
string
Filter to return only jobs created after this date/time (ISO 8601 format).
boolean
When set to true, only return batch jobs created by the API caller. Default is false.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CAMPAIGNSList observability campaigns, optionally filtering them by a text query.

Input Parameters

integer
Page number to return.
string
Optional text query used to filter campaigns.
integer
Maximum campaigns to return on this page (0-100).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CAMPAIGN_SELECTED_EVENTSList chat-completion events selected by an observability campaign.

Input Parameters

integer
Page number to return.
integer
Maximum selected events to return on this page (0-100).
string
required
UUID of the campaign whose selected events should be listed.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CHAT_COMPLETION_FIELDSList fields and operators available for observability event filtering.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CONNECTORSList custom MCP connectors without returning connection secrets.

Input Parameters

string
Cursor from the previous page.
integer
Connectors per page.
object
Non-secret connector filters.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CONNECTOR_TOOLSList tools exposed by an MCP connector.

Input Parameters

integer
One-indexed result page.
boolean
Return the provider’s simplified tool shape.
boolean
Refresh tools from the MCP server.
integer
Tools per page.
string
Named connector credentials to use for discovery.
string
required
Connector UUID or name.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_CONVERSATIONSList all created conversations (Beta). Use to retrieve conversation history or manage existing conversations. Supports pagination and metadata filtering.

Input Parameters

integer
Page number of results to return (0-indexed). Default is 0.
string
Filter conversations by metadata. Exact format depends on your metadata structure.
integer
Number of conversations to return per page (1-1000). Default is 100.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_DATASET_IMPORT_TASKSList import tasks associated with an observability dataset.

Input Parameters

integer
Page number to return.
integer
Maximum import tasks to return on this page (0-100).
string
required
UUID of the dataset whose import tasks should be listed.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_DATASET_RECORDSList conversation records stored in an observability dataset.

Input Parameters

integer
Page number to return.
integer
Maximum records to return on this page (0-100).
string
required
UUID of the dataset whose records should be listed.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_DATASETSList observability datasets, optionally filtering them by a text query.

Input Parameters

integer
Page number to return.
string
Optional text query used to filter datasets.
integer
Maximum datasets to return on this page (0-100).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
Pagination cursor: file ID to start after. Use to retrieve the next page of results.
integer
Maximum number of files to return, must be >=1. Default is server-side limit.
string ("asc" | "desc")
Order to list files: ‘asc’ for ascending or ‘desc’ for descending. Default ‘desc’.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_JUDGESList saved observability judges with filtering, search, and pagination.

Input Parameters

integer
Page number to retrieve.
string
Text search applied to judges.
integer
Maximum judges per page (0-100).
array
Judge output types to include.
array
Model names to include.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
(Beta) Maximum number of libraries to return per page. May not be honored in beta.
string
(Beta) Token for fetching the next page of results. May not be honored in beta.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
Page number to retrieve (0-indexed). Use with page_size for pagination.
integer
Number of documents per page. Defaults to 100 if not specified.
string
required
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique identifier (UUID) for the document library. Obtain this from the List Libraries action or from the library URL in Le Chat.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_VOICESList saved voices without sample audio data.

Input Parameters

integer
Maximum number of voices to return.
integer
Pagination offset.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_WORKFLOW_DEPLOYMENTSList workflow worker deployments, optionally filtering to active deployments or a workflow.

Input Parameters

boolean
Whether to return only active deployments.
string
Filter deployments by workflow name.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_WORKFLOW_EVENTSList durable workflow lifecycle and task events with cursor pagination, filtered by a root workflow execution, workflow execution, or workflow run ID.

Input Parameters

integer
Maximum number of events to return.
string
Cursor returned by a previous page.
string
Filter by workflow run ID.
string
Filter by workflow execution ID.
string
Filter by root workflow execution ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_WORKFLOW_REGISTRATIONSList workflow registrations with sharing, activity, archival, and cursor filters.

Input Parameters

integer
Maximum number of registrations to return.
string
Pagination cursor returned by a previous page.
boolean
False excludes archived, true returns only archived, and null includes all.
string
Filter by task queue.
boolean
Whether to return only active workflow registrations.
string
Filter by workflow UUID.
boolean
Whether to include each workflow definition.
boolean
Whether to include shared workflow registrations.
Filter by workflow name.
boolean
Filter to workflows compatible with chat assistant.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_WORKFLOW_RUNSList workflow runs with status, search, and cursor pagination filters.

Input Parameters

Search by workflow name, display name, or ID.
string
Filter by one or more workflow execution statuses.
integer
Number of runs to return per page.
string
Token returned by a previous page.
string
Filter by workflow name or ID.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_LIST_WORKFLOW_SCHEDULESList workflow schedules with timing, time zone, and execution policy details.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_QUERY_WORKFLOW_EXECUTIONInvoke a read-only query handler on a running workflow execution.

Input Parameters

string
required
Name of the workflow query handler to invoke.
object
JSON object matching the selected query handler’s input schema. Inspect the workflow definition to discover that handler-specific schema.
string
required
ID of the workflow execution to query.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
string
required
The unique UUID identifier of the document to reprocess. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

boolean
Whether to persist the conversation results to the server. Defaults to true
string
required
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.)
boolean
Enable response streaming for real-time output. Defaults to false
object
Additional metadata to associate with the restarted conversation
string
Version of the agent to use when restarting the conversation
string
required
ID of the entry from which to restart the conversation. The conversation will be recreated from this point
object
White-listed arguments from the completion API to configure the response generation (e.g., temperature, max_tokens)
string
required
ID of the original conversation which is being restarted
string ("client" | "server")
Handoff execution mode for agent handoffs.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
required
UUID of the file to retrieve. Obtain file IDs from the List Files action.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_SEARCH_CHAT_COMPLETION_EVENTSSearch observability chat completion events and return previews or only IDs.

Input Parameters

string
Opaque cursor from a previous events result page; ignored for ids.
integer
Maximum events to return when result_format is events (0-100).
array
Additional event fields to include in each result.
string ("events" | "ids")
Return full event previews or only matching event identifiers.
object
required
Search object with required filters. Use a condition with field, op, and value, or nest conditions in AND/OR arrays. Example: {"filters":{"AND":[{"field":"model","op":"eq","value":"mistral-large"}]}}. Operators: lt, lte, gt, gte, startswith, istartswith, endswith, iendswith, contains, icontains, matches, notcontains, inotcontains, eq, neq, isnull, includes, excludes, len_eq.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
Name for the conversation to help identify it later.
string
Specifies which base model to use. Either ‘model’ or ‘agent_id’ must be set. Examples: ‘mistral-small-latest’, ‘mistral-large-latest’, ‘mistral-medium-latest’.
boolean
Whether to persist the conversation history. Set to false to prevent cloud storage. Default is true.
array
Available tools for the conversation (FunctionTool, WebSearchTool, CodeInterpreterTool, etc.). Array of tool definition objects.
string
required
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.
boolean
Set true for streaming responses as Server-Sent Events. Default is false (returns complete JSON response).
string
ID of an agent to use instead of a base model. Either ‘model’ or ‘agent_id’ must be set.
object
Custom key-value metadata to attach to the conversation for tracking or organization.
string
Description of the conversation purpose or context.
string
System instructions to guide the conversation behavior and style.
string
Specific agent version to use. Only applicable when ‘agent_id’ is specified.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_UNARCHIVE_FINE_TUNED_MODELRestore an archived fine-tuned model.

Input Parameters

string
required
Fine-tuned model identifier.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
Updated name for the agent
string
Updated model to use for the agent (e.g., ‘mistral-large-latest’, ‘mistral-small-latest’)
array
Updated list of tools available to the model during conversation
string
required
The unique identifier of the agent to update
array
Updated list of handoff configurations
object
Updated custom metadata to associate with the agent
string
Updated description of the agent’s purpose
string
Updated instruction prompt the model will follow during the conversation
object
White-listed arguments from the completion API.
boolean
Updated flag indicating if agent is deployed for chat

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

integer
required
Version number to set as the current version. Must be a non-negative integer from the agent’s available versions list.
string
required
Unique identifier of the agent to update (e.g., ‘ag_019c5ecef27c7721a09ec60a67fceee5’)

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: MISTRAL_AI_UPDATE_FINE_TUNED_MODELUpdate the name or description of a fine-tuned model.

Input Parameters

string
New model name.
string
required
Fine-tuned model identifier.
string
New model description.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
New name for the library. If not provided, the current name is retained.
string
required
Unique identifier (UUID) of the library to update
string
New description for the library. If not provided, the current description is retained.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

string
New name for the document. If provided, this will replace the current document name.
object
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.
string
required
The unique UUID identifier of the library containing the document. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).
string
required
The unique UUID identifier of the document to update. Must be a valid UUID format (e.g., xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx).

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

object
required
File to upload to Mistral AI.
string ("fine-tune" | "batch" | "ocr")
Purpose for the uploaded file.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not
Slug: 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

object
required
File to upload. Supported formats include PDF, TXT, DOC, DOCX, and other common document types.
string
required
Unique identifier (UUID) of the library where the document will be uploaded. Use MISTRAL_AI_LIST_LIBRARIES to get available library IDs.

Output

string
required
Data from the action execution
string
Error if any occurred during the execution of the action
boolean
required
Whether or not the action execution was successful or not