TEKIZ.AI plans

Choose how your team uses AI.

Paid plans include requests on TEKIZ.AI-hosted capacity when it is available. You can also connect your existing model accounts and local tools. For sensitive work, tell us what a private setup needs to do before you choose a plan.

We confirm pilot availability and price before you commit. Explore the marketplace.

Your AI setup

Bring the services you already use.

When live capacity is available, every paid plan includes hosted inference. You can also connect your own model services and local models. TEKIZ.AI manages the API key, routing rules, and request record. Providers you connect bill their own usage and process requests under their own terms.

Checking availability. Status

Use your own providers

Connect Ollama alongside the services you approve.

A single local model can run directly. TEKIZ.AI helps when your team uses several local and cloud services and needs one API key, routing rules, and a record of each request.

Lite, Pro, and Max include hosted inference within their monthly request allowances when capacity is available. A provider account you connect stays on that provider's bill. If you need a private setup with one bill, Request managed access. We review it as a separate pilot.

Lite
$6 / month

For people and small businesses connecting their own model accounts or local models.

  • 10,000 monthly inference requests included
  • Use hosted capacity or providers you approve
  • 60 routing requests per minute
  • Choose from the model accounts you connect
  • Use another approved option when the first one is unavailable
  • Basic usage history and account controls
Try 10 requests free
Max
$72 / month

For higher request volume and help planning a private setup.

  • 200,000 monthly inference requests included
  • Use hosted capacity or providers you approve
  • 600 routing requests per minute
  • Priority eligible capacity when it is available
  • Help with private setup and rollout planning
Try 10 requests free

What TEKIZ.AI handles

One API for the services you choose.

Set rules for different kinds of work. TEKIZ.AI uses those rules to choose a service and records where each request went.

One-vendor setup

A provider change, outage, or policy decision can affect every workflow at once.

Approved service choices

Your team chooses the services that are allowed for the work. If no approved choice is available, the request can stop for a person to decide.

What stays yours

Your provider account, provider bill, approval rules, and the record of what happened remain under your control.

10,000
60%
3
One-vendor default 10,000

requests rely on one provider account

With approved choices 4,000

requests remain on the first choice; 6,000 can use 2 other approved choices

Illustrative only. Actual routing depends on your rules, task requirements, connected accounts, service health, and provider limits. TEKIZ.AI does not increase a provider's quota.

Business plans

Need tighter rules for sensitive work?

Teams in law, healthcare, finance, and government often need to show where work went, who approved the service, and what happened.

We scope business plans around the people using the service and the controls they need. Request volume informs capacity planning. A Canadian sovereign deployment is offered after its residency, encryption, and evidence controls have been verified for that deployment.

Managed model access

Want us to manage model access too?

Tell us which models and usage you need. We'll review a managed setup separately and confirm availability and price before you pay.