Whatever message this page gives is out now! Go check it out!
Mistral AI: LLM configuration field reference
Last update:
May 18, 2026
This document describes settings for the Mistral AI provider in the LLM configuration UI: basic connection, model parameters, proxy, and advanced options.
Behavior notes
- Leaving numeric or optional text fields blank uses the provider or integration default for that parameter.
- API key and logging fields include inline security guidance in the descriptions below (suitable for UI help text).
For official Mistral concepts (models, API, endpoints), see Mistral AI documentation.
Basic configuration
Field | Description |
|---|---|
Config alias | Required. Unique name for this configuration. Use only letters, numbers, hyphens, and underscores (for example mistral-prod-eu). |
Provider | Mistral AI. The provider for this saved configuration. |
Model name | Required. The model identifier Mistral expects for this integration (for example mistral-small-latest or another documented model id). Use the exact string your deployment and API version support. |
API key | Optional. Leave blank to supply the key at runtime. If you enter a key, it is stored with this configuration—treat it as a secret and follow your organization’s access and rotation rules. Create and rotate keys in the Mistral AI console or your team’s secret store. |
Base URL | Optional. Use Mistral’s default API base unless you route traffic through a proxy, regional endpoint, or compatible gateway. When set, use the root URL your client library or HTTP stack expects for chat or completion calls. |
---
Model parameters
These control sampling and output shape for requests to Mistral.
Field | Description |
|---|---|
Temperature | Leave blank to use the default. When set, use 0 or greater. Higher values increase randomness; typical ranges depend on the model—see Mistral’s API reference for supported bounds. |
Max tokens | Leave blank to use the default. When set, enter a positive integer for the maximum number of tokens in the model response (subject to model and plan limits). |
Top P | Leave blank to use the default. When set, use 0 or greater (often 0–1). Nucleus sampling; unsupported values may be rejected or ignored depending on the API. |
Presence penalty | Leave blank to use the default. When set, use 0 or greater. Reduces likelihood of introducing new topics that already appeared in the context, per Mistral’s parameter semantics. |
Seed | Leave blank to use the default. When set, use a positive integer when you need more repeatable outputs and the model supports a seed; behavior can vary by model. |
Response format | Default or structured output when your integration requests JSON or another supported format. Leave Default unless your workflow depends on structured responses. |
Stop sequences | Optional. Comma-separated sequences that stop generation (for example END or newline tokens your API accepts). |
---
Proxy settings
Field | Description |
|---|---|
Proxy host | Optional. HTTP proxy hostname or IP. If you set a host, you must set Proxy port. |
Proxy port | Optional. Integer from 1 through 65535. Required when proxy host is set. |
Proxy username | Optional. User name for proxy authentication. Leave blank if the proxy does not require credentials. |
Proxy password | Optional. Proxy password. Stored credentials are sensitive—follow your organization’s secret-handling rules. Leave blank if not required. |
---
Advanced settings
Field | Description |
|---|---|
Max retries | Leave blank to use the default. When set, enter a positive integer for how many times to retry a failed request to the Mistral API. |
Timeout (seconds) | Leave blank to use the default. When set, enter a positive integer for the maximum wait time per request. |
Log API requests | When enabled, request details are written to logs. Requests can include prompts, headers, and identifiers—use only while troubleshooting and disable afterward. Follow your organization’s logging and privacy requirements. |
Log API responses | When enabled, response details are written to logs. Responses can contain generated text and personal data—use only while troubleshooting and disable afterward. Follow your organization’s logging and privacy requirements. |
---
Parameters not shown for Mistral in the default form
Your full product matrix may expose additional controls for other providers (for example frequency penalty, top K, or provider-only flags). For Mistral, frequency penalty and top K are typically omitted or not applicable in the same way as on other providers—see
LLM_PROVIDER_PARAMETERS.md for the Mistral column (Y / --).---
Related reference
- Parameter inventory and validation rules:
LLM_PROVIDER_PARAMETERS.md(Mistral column: Y = supported, -- = not shown for that provider).
We're glad. Tell us how this page helped.
We're sorry. Can you tell us what didn't work for you?
Share additional feedback to help us improve.
0/255
|
