Get your API key
Sign in once. No card required. Create a key and try TEKIZ.AI.
- Account
- API key
- Access
- Try it
No password needed.
Pro Create key firstMore options
Choose a plan
Your selection is saved and applied after sign-in.
Preview setup
Use password sign-in instead
Account
Loading...
Create an API key, check that it works, then send your first request.
Setup progress
See what is left to do. A key check confirms access, and a test request confirms TEKIZ.AI is working.
Sign in to manage your keys and plan.
Create at least one active sk_tekiz_* key.
Choose Lite, Pro, or Max to start using TEKIZ.AI.
Check /v1/models before connecting an app.
Send a test request from this browser.
Connect a client
Your first request worked. Copy the Codex setup or choose another supported client.
Account details
Share with support
Copy a short account summary for support. It includes your plan, usage limits, and account status. It never includes prompts, credentials, API keys, cookies, model responses, or customer data.
Usage
Loading current billing period...
API key
Your browser generates a private confidential-key suffix and sends only its signed public commitment to TEKIZ.AI. The full bundle appears here once; save it in a password manager or the signed confidential client.
Connect your app
OPENAI_BASE_URL=https://api.tekiz.ai/v1
ANTHROPIC_BASE_URL=https://api.tekiz.ai
Available models depend on your plan and the services you connect. You can keep using your own provider keys.
Run a Community node
Share an installed model - from Ollama or an OpenAI-compatible server like vLLM - when your machine is idle. We review each node before it can accept work.
Your nodes
Loading node status...
Accepted work
Loading accepted-work ledger...
This is a prompt-free reconciliation record, not earnings or a payout balance. Rates and payouts are not available in the Community alpha.
Check one model
This reads local model server and hardware details without loading a model, changing files, or contacting TEKIZ.AI.
Setup allows one job and one resident model at a time. Admission is based on measured RAM/VRAM and the operator's declared model limit - 34B is a conservative default that can be raised after a verified capacity review.
Request access
Create a temporary setup code for this computer. It stays offline until it has been reviewed.
Start your node
The runner makes outbound requests only and accepts work within the limits checked above. It authenticates with the scoped node credential created during enrollment; it does not need a TEKIZ.AI API key in its environment.
./tekizai-community run
Community routing consent
Set the durable upper bound for Community execution in this account. Empty selections deny Community routing. Plan and node security checks still apply, and every change is recorded.
Community operators may see plaintext while executing non-TEE work. Selecting a non-Canadian residency explicitly permits that cross-border location; it does not bypass your plan or capacity restrictions.