Models

Use the models you already have from one endpoint.

Connect OpenAI, Anthropic, Gemini, Ollama, NVIDIA NIM, OpenRouter, or a private model service. TEKIZ.AI gives your tools one model list and tries another available option when one stops working.

Create API key Recover API key Read quickstart Fusion Ask about one subscription Configure Codex View catalog JSON View pricing Compare gateways

Sign in, create an API key, then connect your models. Choose a plan when you need more requests.

You can browse this list without signing in. Your complete model list and model requests stay private to your API key.

Create API key next
Profiles

Stable model names

tekizai/auto, tekizai/balanced, and tekizai/frontier let your tools keep the same settings while TEKIZ.AI chooses an available model. tekizai/fusion is available when the models it needs are online.

BYOK

Your models and subscriptions

Connect provider keys, subscriptions, local models, or team-approved services you are allowed to use. Your personal provider accounts are never shared with other customers.

Failover

Automatic backup

TEKIZ.AI can use an available cloud, Tailnet, or private installation when another one is down. Your credentials remain on the computer where you connected them.

Browse models

Find a model or profile.

This public list shows model families and examples. Sign in to see the models connected to your account.

Catalog JSON
Loading catalog... Loading model list.
Family Example models How access works
TEKIZ.AI profiles tekizai/auto, tekizai/frontier, tekizai/fusion Stable names choose among the models you can use. Fusion is available on Pro and Max when its task and review models are online. See the guide.
OpenAI and Codex-compatible gpt-5.5, gpt-5.4, gpt-5.4-mini Connect your API key or a compatible Codex/OpenClaw account. Codex setup works with TEKIZ.AI cloud or local port 8790.
Anthropic-compatible claude-opus, claude-sonnet, claude-haiku Connect an Anthropic or Dario account you are allowed to use. Personal accounts are never shared.
Google Gemini gemini-3-pro, gemini-3-flash, gemini-2.5-pro Connect your Google API key or Vertex account.
Ollama and Ollama Cloud llama3.3, qwen3-coder, gpt-oss:cloud Use local Ollama models or models from your Ollama Cloud account.
OpenAI-compatible BYOK nvidia-nim/nemotron, openrouter/free-models, darkbloom/custom Connect your keys for NVIDIA NIM, OpenRouter, or a compatible private service.

Client setup

Connect with your API key.

Choose a model family here, then use your account key to see the models available to you:

OPENAI_BASE_URL=https://api.tekiz.ai/v1

OPENAI_API_KEY=sk_tekiz_...

curl -H "Authorization: Bearer $OPENAI_API_KEY" https://api.tekiz.ai/v1/models