Use your own Mistral key
Put your authorized MISTRAL_API_KEY on a router you control. Your Mistral account controls access to Codestral and other Mistral models.
Mistral AI routing
Run TEKIZ.AI on your machine or private server with your Mistral key. Coding work can use Codestral while another approved model handles requests when needed. Hosted access uses a separate TEKIZ.AI key and the models available to your account.
Put your authorized MISTRAL_API_KEY on a router you control. Your Mistral account controls access to Codestral and other Mistral models.
For the hosted API, point OpenAI-compatible apps at https://api.tekiz.ai/v1. Hosted requests use routes available to your account. To use your own Mistral credentials, configure them on a local router.
Send code tasks to your Codestral or Mistral models, with stronger, longer-context, or local models available when needed.
This tests your hosted TEKIZ.AI key with automatic routing. To use Mistral with your own credentials, set up a local router and configure the credentials on that router.
export OPENAI_BASE_URL=https://api.tekiz.ai/v1
export OPENAI_API_KEY=sk_tekiz_your_generated_key
curl "$OPENAI_BASE_URL/chat/completions" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tekizai/auto",
"messages": [{"role": "user", "content": "Explain how to make this function easier to test."}]
}'
Add multiple authorized Mistral keys. TEKIZ.AI shares requests across keys that are working and pauses only the key that fails.
If Mistral rate-limits a request, TEKIZ.AI can try another configured key, provider, or eligible local model.
Images, audio, video, and documents are sent only to models that can handle that kind of input.
Your own Mistral account and Mistral billing stay separate from hosted TEKIZ.AI access. On a router you control, TEKIZ.AI can try another eligible model when you configure one.
Create an API key, copy the hosted quickstart, use the coding-agent setup, or estimate routing fit.
If your company approves only Mistral, keep that boundary. TEKIZ.AI can reduce token burn by choosing eligible models. Your Mistral account handles provider billing.