Compare AI setups

Compare TEKIZ.AI with hosted gateways.

Run a TEKIZ.AI router to connect approved provider accounts, local Ollama, and private servers through one API. Your provider credentials stay on infrastructure you control. A hosted account uses a TEKIZ.AI key for the models available to your plan.

Run with your providers Create hosted API key Migration guide Fusion compatibility Compare plans Compare OpenRouter Check service status Estimate plan use Discuss a private setup
Recover API key

This link opens a hosted account. Create a key and check /v1/models for availability. Use the local router for provider credentials you control.

Connect only provider accounts and subscriptions you are allowed to use. TEKIZ.AI does not bypass provider terms.

Evaluating OpenRouter specifically? Read the focused TEKIZ.AI vs OpenRouter comparison for hosted catalog access and private model setups.

Keep provider keys where you control them.

With a local or private router, provider keys can stay on your machine, server, or Tailnet. A hosted TEKIZ.AI account has its own API keys and billing.

Choose what happens during an outage.

On a router you run, set an order of approved services for each kind of work. The router can consider provider health, response time, and model fit. Connect compatible tools such as Codex, OpenClaw, Cursor, Aider, and Continue.

Use local models with cloud services.

A router you run can connect local Ollama, Ollama Cloud, private services, and cloud providers your team authorizes.

What changes with TEKIZ.AI?

Need TEKIZ.AI Hosted model gateway
Where provider keys live Provider keys can stay on a router you control when you choose a local or private setup. Typically centralized through the hosted API account.
Coding tool support Connect compatible clients, including Codex, OpenClaw, Cursor, Aider, Continue, and OpenHands. See the setup guide for each tool. Strong hosted OpenAI-compatible API story.
Local models A router you run can use local Ollama alongside approved cloud providers. Your rules decide which requests may leave your environment. Usually focused on remote hosted model providers.
Provider selection On your router, use your team's rules, provider health, response time, model capability, and task type to choose a service. Model catalog selection and provider routing through hosted infrastructure.
Fusion / compound answers Available on eligible Pro and Max setups. Use tekizai/fusion or the tekizai:fusion server tool to derive independent tasks, run them in parallel, and review the result. Compound routing can expose a hosted multi-model workflow.
Resilience model A private router can stay behind the public API edge. Where configured, TEKIZ.AI can select a healthy router on your Tailnet. Depends on the hosted provider platform and upstream provider health.
Hosted SaaS Hosted sign-in, TEKIZ.AI API keys, usage limits, request history, billing, and service status. Mature hosted account and billing experience.
Best fit Teams that want to run a router with their own approved providers or local models, or use the models available through a hosted account. Hosted model marketplace access with minimal local infrastructure.

How to switch

Keep one API address for your tools.

For hosted access, create an account key and check /v1/models before connecting a tool. For your own providers or local models, run the router on infrastructure you control and point the tool at its local endpoint. 

export OPENAI_BASE_URL="https://api.tekiz.ai/v1"
export OPENAI_API_KEY="sk_tekiz_..."

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": "Explain how to set a request timeout."}]
  }'
Copy setup first. Paste the bundle into your current OpenAI-compatible client, then replace the placeholder with your generated sk_tekiz_* key.

Hosted plans

Hosted plans for available TEKIZ.AI models

Hosted plans provide account API keys, usage limits, request history, and support. Check /v1/models for current model availability. A customer-controlled router can use your provider accounts and local models after a private setup review.

  • Lite: hosted access and activity visibility for individual workflows.
  • Pro: advanced model choices, Fusion when capacity is live, service-order controls, and activity records for development work.
  • Max: high-volume automation, priority service order, Fusion when capacity is live, and team use.
  • Max implementation review: ask for migration help or private deployment support. Managed model access requires provider authorization, confirmed pricing, quotas, audit records, and acceptable-use controls. Request private-beta review.