Skip to main content

Using Mistral AI With PostQode

PostQode supports accessing models through the Mistral AI API, including both standard Mistral models and the code-specialized Codestral model.

Website: https://mistral.ai/

Getting an API Key

  1. Sign Up/Sign In: Go to the Mistral Platform. Create an account or sign in. You may need to go through a verification process.
  2. Create an API Key:

Supported Models

PostQode supports the following Mistral models:

Model IDModel Default TemperatureFunction CallingVision / Image support
codestral-latest0.3
devstral0.3
mistral-large-latest0.7
ministral-8b-latest0.3
ministral-3b-latest0.3
mistral-small-latest0.3
pixtral-large-latest0.7
The default model temperature in PostQode is 0.0, so you should consider experimenting with temperature adjustments!

Note: Model availability and specifications may change. Refer to the Mistral AI documentation and Mistral Model Overview for the latest information.

Configuration in PostQode

  1. Open PostQode Settings: Click the gear icon () in the PostQode panel.
  2. Select Provider: Choose "Mistral" from the "API Provider" dropdown.
  3. Enter API Key: Paste your Mistral API key into the "Mistral API Key" field if you're using a mistral model. If you intend to use codestral-latest, see the "Codestral" section below.
  4. Select Model: Choose your desired model from the "Model" dropdown.

Using Codestral

Codestral is Mistral's flagship model specifically tuned for code generation, inline completion, and test automation. Only for Codestral you can use dedicated endpoints (Default: https://codestral.mistral.ai). For standard La Plateforme keys, use Base URL: https://api.mistral.ai.

To use Codestral:

  1. Select "Mistral" as the API Provider.
  2. Select a Codestral Model
  3. Enter your Codestral (codestral.mistral.ai) or La Plateforme (api.mistral.ai) API Key.