Use your own Mistral key
Connect Mistral with your own MISTRAL_API_KEY. TEKIZ.AI
Router does not grant Mistral, Codestral, or La Plateforme access.
Mistral AI routing
Connect your MISTRAL_API_KEY and point your apps at TEKIZ.AI
Router. Coding tasks can use Codestral, while another model can take
over when a key or model is unavailable.
Connect Mistral with your own MISTRAL_API_KEY. TEKIZ.AI
Router does not grant Mistral, Codestral, or La Plateforme access.
Point OpenAI SDKs, Codex, Cursor, Aider, Continue, OpenHands, and
compatible apps at https://api.tekiz.ai/v1. TEKIZ.AI
Router can use Mistral or another model you connected.
Send code tasks to your Codestral or Mistral models, with stronger, longer-context, or local models available when needed.
export OPENAI_BASE_URL=https://api.tekiz.ai/v1
export OPENAI_API_KEY=sk_tekiz_your_generated_key
export MISTRAL_API_KEY=your_authorized_mistral_key
curl "$OPENAI_BASE_URL/chat/completions" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "tekizai/code",
"messages": [{"role": "user", "content": "Use Mistral or Codestral if it is the best healthy authorized route"}]
}'
Add multiple authorized Mistral keys. TEKIZ.AI shares requests across keys that are working and pauses only the key that fails.
When Mistral is rate-limited, TEKIZ.AI can try another key, provider, local Ollama model, or private model you allowed.
Images, audio, video, and documents are sent only to models that can handle that kind of input.
TEKIZ.AI provides routing, API keys, usage limits, account tools, request history, and backups. It does not include Mistral access or bypass Mistral terms.
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 while making better use of existing subscriptions and account billing.