Mistral AI

Get Prompt Response

This action retrieves the response generated by the specified model based on the given prompt.

Get Raw Response

This action retrieves the unformatted (raw) response generated by the selected model for a given prompt.

Generic Action

This is a generic action used to make requests to any Mistral AI endpoint.

API Token

Enter the API token to authenticate to Mistral AI.

Password

Required

Temperature

Enter the sampling temperature (a number between 0 and 2). Higher values (example 0.8) make the output more random, while lower values (example 0.2) make it more focused and deterministic.

Float

Optional

Default value:

1

Verify

Choose your preference to verify SSL or TLS while making requests. It is recommended to set this option to yes. Passing no may result in connection errors.

Boolean

Optional

The allowed values are true and false. By default, verification is enabled.

Base URL

Enter the base URL to access Mistral AI API.

Example:

https://api.mistral.ai/v1

Text

Optional

Default value:

https://api.mistral.ai/v1

Timeout

Enter the timeout value in seconds. This is the number of seconds that requests will wait to establish a connection with Mistral AI.

Integer

Optional

Allowed range:

15-120

Default value:

15

Max Tokens

Specify the maximum number of tokens to generate before stopping. Each model has different maximum values for this parameter.

Integer

Optional

Default value:

1024

Model 

Specify the model name to use for generating the response.

Example:

codestral-latest

Single-select

Required

Allowed values:

codestral-latest, mistral-large-latest, pixtral-large-latest, mistral-saba-latest, ministral-3b-latest, ministral-8b-latest, mistral-embed, mistral-moderation-latest, mistral-ocr-latest, mistral-small-latest, pixtral-12b-2409, open-mistral-nemo, open-codestral-mamba

Prompt 

Provide the text prompt that will be sent to the selected model for response generation.

Text Area

Required

Model 

Select the model to use for generating the response.

Example:

open-mistral-nemo.

Single-select

Required

Allowed values:

codestral-latest, mistral-large-latest, pixtral-large-latest, mistral-saba-latest, ministral-3b-latest, ministral-8b-latest, mistral-embed, mistral-moderation-latest, mistral-ocr-latest, mistral-small-latest, pixtral-12b-2409, open-mistral-nemo, open-codestral-mamba

Messages 

Enter a list of messages that define the conversation context.

Example:

messages: $JSON[[{'role': 'user', 'content': 'hello!'}]]

List

Required

Each message must include a role (system, user, assistant, or tool) and content.

Response format 

Enter the format in which you want the response to be returned.

Example:

{'type': 'text'}.

Text_area

Optional

Allowed formats:

text, json_object, and json_schema

Method

Enter the HTTP method to make the request.

Text

Required

Allowed values:

GET, PUT, POST, and DELETE.

Endpoint

Enter the endpoint to make the request to.

Example:

responses

Text

Required

Query Params

Enter the query parameters to pass to the API.

Key Value

Optional

Payload

Enter the payload to pass to the API.

Any

Optional

Extra Fields

Enter the extra fields to pass to the API.

Key Value

Optional

Allowed keys:

payload_json, download, files, filename, retry_wait, retry_count, custom_output, and response_type.

v2.0.0