Mistral AI Integration

Connect Helicone with Mistral AI, a platform that provides state-of-the-art language models including Mistral-Large and Mistral-Medium for various AI applications.

You can follow their documentation here: https://docs.mistral.ai/

Gateway Integration

1

Create a Helicone account

Log into helicone or create an account. Once you have an account, you can generate an API key.

2

Create a Mistral AI account

Log into console.mistral.ai or create an account. Once you have an account, you can generate an API key from your dashboard.

3

Set HELICONE_API_KEY and MISTRAL_API_KEY as environment variable

HELICONE_API_KEY=<your API key>
MISTRAL_API_KEY=<your API key>

4

Modify the base URL and add Auth headers

Replace the following Mistral AI URL with the Helicone Gateway URL:

https://api.mistral.ai/v1/chat/completions -> https://mistral.helicone.ai/v1/chat/completions

and then add the following authentication headers:

Authorization: Bearer <your API key>

Now you can access all the models on Mistral AI with a simple fetch call:

Example

curl \
  --header 'Authorization: Bearer <MISTRAL_API_KEY>' \
  --header 'Content-Type: application/json' \
  --data '{
    "model": "mistral-large-latest",
    "messages": [{"role": "user", "content": "Say this is a test"}]
}' \
  --url https://mistral.helicone.ai/chat/completions

For more information on how to use headers, see Helicone Headers docs. And for more information on how to use Mistral AI, see Mistral AI Docs.