Bring your NVIDIA API key

Connect your own NVIDIA_API_KEY. TEKIZ.AI provides routing and account history; it does not grant or resell NVIDIA access.

OpenAI-compatible setup

Point OpenAI SDKs, coding agents, and gateway-compatible clients at https://api.tekiz.ai/v1 while the router chooses NVIDIA NIM, Ollama, OpenAI, Gemini, Anthropic, or private routes by policy.

Keep working when an account is busy

When an NVIDIA key or model is rate-limited, TEKIZ.AI can try another model you are allowed to use.

Set up NVIDIA NIM setup

export OPENAI_BASE_URL=https://api.tekiz.ai/v1
export OPENAI_API_KEY=sk_tekiz_your_generated_key
export NVIDIA_API_KEY=nvapi-your_authorized_key

curl "$OPENAI_BASE_URL/chat/completions" \
  -H "Authorization: Bearer $OPENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tekizai/frontier",
    "messages": [{"role": "user", "content": "Use NVIDIA NIM if it is the best healthy authorized route"}]
  }'

Credential load balancing across your keys

Add more than one NVIDIA API key. TEKIZ.AI spreads requests across keys that are working and pauses only a key that is exhausted or rate-limited.

Send files to services that accept them

Images, audio, video, and documents are sent only to models that can handle that kind of input.

Profiles avoid incompatible models

Automatic profiles can include NVIDIA NIM without sending images, audio, video, or documents to models that cannot handle them.

Why put TEKIZ.AI in front of NVIDIA NIM?

Your tools keep one address while TEKIZ.AI checks your keys, sends files to compatible models, and uses an available local or cloud backup when NIM cannot take the request.

Next steps

Create an API key, copy the hosted quickstart, browse NVIDIA-capable routes, or read the NVIDIA NIM integration guide.

Stay within your approved services

If your company approves only NVIDIA AI, keep that boundary. TEKIZ.AI can reduce token burn while making better use of existing subscriptions and account billing.