Fast track evaluation
Evaluate the Fully Managed tier in an afternoon: first routed request in about 15 minutes after onboarding; a small team and cost readout by the end of the day. Nothing to install.
What this evaluation covers
Tetrate Agent Router is an AI gateway between your apps or coding agents and providers (OpenAI, Anthropic, and others). One OpenAI-compatible endpoint handles routing, credentials, cost, and policy; every request is recorded and attributed to the key that made it.
On the Fully Managed tier, Tetrate runs both the management plane and the data plane, so the evaluation starts at first sign-in.
Results are only convincing on real traffic. The fast track routes work you already pay for. Your own provider account via Bring Your Own Key (BYOK), or a Claude Pro/Max plan via passthrough mode through the gateway. Upstream billing stays as before; Agent Router observes and attributes the traffic. Nothing is locked in; you can stop at any point.
By the end, the environment produces:
- Real traffic flowing through the gateway, still billed upstream as before (BYOK or Claude Code passthrough mode).
- A cost and token breakdown per request, model, and key, with a monthly projection.
- A budget with a live meter, and multiple teammates routing through the same gateway.
The result is the raw material for a rollout decision: what current AI usage actually costs, where it goes, and how it compares across a team.
Before you begin
- Check the product overview page for more information.
- Or, consult the where to begin page as a starting point.
The fast track assumes the following are on hand.
Note: URLs below use <your-tenant> for the tenant hostname segment Tetrate assigned; Fully Managed evaluation tenants look like tare-pn-<xxxxxxxx> (for example tare-pn-a1b2c3d4).
- The Admin Dashboard URL Tetrate provided for the evaluation tenant, for example
https://dashboard.<your-tenant>.tetrate.ai. The Admin Dashboard is the operator view: onboarding, identity, providers, models, budgets, and Agent Router settings. - The Dev Console URL Tetrate provided for the evaluation tenant, for example
https://router.<your-tenant>.tetrate.ai. The Dev Console is the developer view: API keys, the proxy endpoint, request logs, and usage. - The Data Plane URL Tetrate assigned for the evaluation tenant, for example
https://proxy.<your-tenant>.tetrate.ai. Enter it in the onboarding wizard; later copy the same host from the Dev Console (usually with/v1) as the proxy endpoint apps and agents call. - An LLM provider API key, for example an OpenAI or Anthropic key. You add this once during onboarding (Step 1); that key routes real traffic on its own, and you are good to go. Adding a BYOK key (Step 3) is optional — use it only if you want each person's spend billed to their own provider account. Or a Claude Max or Pro subscription if you will use Claude Code passthrough mode instead.
- An identity provider. An Auth0 account works well for an evaluation and takes minutes to set up; corporate IdP admin access can be used instead where it is available and approved. Learn how to set up Auth0 here.
- A terminal or HTTP client (curl, Python, or Postman) for the first request.
Step 1: Initial sign in and onboard (Admin Dashboard)
Access is the first thing the evaluation establishes, because every later action happens under a real signed-in identity. The first sign-in launches a one-time onboarding wizard that configures the organization: single sign-on, at least one provider, and the models to expose.
Single sign-on is configured up front for two reasons. It puts the evaluation on the same footing as a real deployment from the start, and it turns teammate onboarding later in the fast track into a single shared link with no separate account administration. Auth0 is recommended for an evaluation because it stands up an identity provider in minutes without waiting on corporate IT. The configuration is identical to a corporate IdP, so nothing about the evaluation changes if the tenant later moves to permanent corporate SSO.
- Open the Admin Dashboard URL (
https://dashboard.<your-tenant>.tetrate.ai) in a web browser of choice. - The first sign-in launches a welcome screen and the onboarding wizard.
- click button Start setup to begin the onboarding. Row numbers in the table below match the wizard screens.
No corporate IdP access? Use auth0.com for evaluation SSO
- At auth0.com, sign up and create a tenant. Go to Applications → Create Application → Regular Web Application. From its Settings, copy the Domain, Client ID, and Client Secret.
- Create an admin user: User Management → Users → Create User with an email you control.
- Skip Application URIs settings for now, and save your work.
- Return to the onboarding
- When you reach wizard step 2 (Corporate Login), click button IdP setup guide and copy the Redirect URI (for example
https://auth.<your-tenant>.tetrate.ai/api/auth/sso/callback/corporate). - In the Auth0 app settings, set Allowed Callback URLs to that Redirect URI, and Allowed Web Origins to your three tenant hostnames (
https://auth.<your-tenant>.tetrate.ai,https://dashboard.<your-tenant>.tetrate.ai,https://router.<your-tenant>.tetrate.ai).
Full walkthrough: Set up Auth0 for evaluation use.
| Wizard step | Section | What to do |
|---|---|---|
| 1 | Configure Organization Name | Set Organization Name and Data plane URL. - Use the value Tetrate assigned (for example https://proxy.<your-tenant>.tetrate.ai, including the scheme).- Tetrate runs the data plane; this only registers the hostname the Dev Console later shows as the proxy endpoint. |
| 2 | Configure Corporate Login | No corporate IdP access? Expand the Auth0 tip above and use those Domain / Client ID / Client Secret values here. Fill in the OIDC values from your IdP (not Tetrate): - Issuer: https://<your-domain>/ (trailing slash)- Client ID: <provided by IdP> - Client Secret: <provided by IdP> - Scopes: openid profile email- Admin emails: at least your email address. - Attribute mapping: Set to email.- Role Mapping (optional): skip for now. click button IdP setup guide and copy the wizard's Redirect URI into your IdP app first. click button Next. |
| 3 | Configure LLM Provider Keys | Enable at least one (1) provider (for example OpenAI or Anthropic). - click button Enable on a provider to which you have access. - Enter your API key into the Provider secret field and click button Rotate to persist it. - Toggle Enable provider to on. - click button Save. |
| 4 | Configure LLM Model | Review the model list. - Leave the defaults as is, or (de)select as needed. - You can change this later in the Admin Dashboard. |
| 5 | Configure AI Gateway | SKIP THIS STEP! Do not click any button or option. Rationale: This is for self-hosted data plane only, and is not applicable to this evaluation. Advance past it by clicking Next. |
| 6 | Complete | click button Complete setup to close the onboarding wizard. |
Tetrate manages the installed data-plane credential for Fully Managed deployments. Regenerating a data-plane credential is a rotation operation that can break the managed data plane. If it is regenerated by mistake, contact Tetrate to restore service.
After onboarding, sign out, then sign back in with SSO as your admin user.
Before moving to the next step, confirm the default project is ready and configured for your use:
Configure the default project
- Log in to the Admin Dashboard (
https://dashboard.<your-tenant>.tetrate.ai). - In the left-hand sidebar, navigate to Directory → Projects.
- Select the default project from the list of projects.
- Note: at this point, only the default project will be visible.
- Select tab Gateway and check the default gateway's endpoint.
- Right after onboarding this is often empty
- If so, edit that gateway and set a name (e.g.
default-gateway) and the URL to your proxy host (https://proxy.<your-tenant>.tetrate.ai). Click button Save.
- Select tab Members and confirm your admin user is a member of the project.
- If not, click button Grant access and add your admin user.
- If no users are displayed, use the search box.
- After selecting your user, click button Grant.
- Verify the selected user is now listed in this tab.
- Select tab Providers and confirm at least one provider is connected and enabled.
- If not, click button Add to project, select one or more providers from the list and click button Add.
- Verify the selected providers are now listed in this tab.
Verify the project configuration
- In the top-left corner, switch to project default by selecting it from the drop-down list (currently set to
Organization). - Navigate to Catalog → Models.
- Confirm the models you plan to call are linked and enabled.
- If not, click button Add to project, select one or more models from the list and click button Add.
- Verify the selected models are now displayed.
Outcome
The Admin Dashboard loads under SSO, the default project points at the managed proxy endpoint, and the providers and models you configured are available to the project.
Relevant resources
Step 2: route your first request (Dev Console)
Before any real traffic runs, a single request confirms the path end to end. Two things are created here. The proxy endpoint is the OpenAI-compatible URL that fronts every configured provider; applications point at it instead of at a provider directly. The API key is the credential a client presents to the gateway, and it is also the unit that request logs, usage, and budgets attribute to, so it is worth naming keys meaningfully.
Because the endpoint is OpenAI-compatible, most existing code and SDKs work by changing only the base URL and the key. The curl and Python examples below are the same request expressed two ways.
Create an API key
- Open the Dev Console (
https://router.<your-tenant>.tetrate.ai) in a web browser. If needed, log in using the account set up in step 1. - In the left-hand sidebar, navigate to Settings → API Keys.
- Click button Add API Key.
- Set field Key type to Inference key from the drop-down list.
- Enter a Key name (e.g.
eval-dev-key1) - Click button Create key.
- From the popup, copy the values of Your API key and base URL to a text editor or note taking app.
- The API key will not be visible again, so verify that you have copied it before continuing.
- Click button Done.
- Note the Base URL is displayed at the top of the page.
- This really is the Data plane URL from Step 1, usually with
/v1— for examplehttps://proxy.<your-tenant>.tetrate.ai/v1.
- This really is the Data plane URL from Step 1, usually with
Test your API key
- Send a request using curl or Python.
- In the code examples, replace
YOUR_PROXY_URLandYOUR_API_KEYwith the values you copied earlier. - In the code examples, replace
gpt-4owith any model in your catalog.
- In the code examples, replace
- curl
- Python
export TARS_API_KEY="<YOUR_API_KEY>"
export BASE_URL="<YOUR_PROXY_URL>"
curl ${BASE_URL}/chat/completions \
-H "Authorization: Bearer $TARS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-4o",
"messages": [{"role": "user", "content": "Hello, world!"}]
}'
from openai import OpenAI
client = OpenAI(base_url="YOUR_PROXY_URL", api_key="YOUR_API_KEY")
resp = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello, world!"}],
)
print(resp.choices[0].message.content)
You should see: a completion, and the request in the Dev Console under Monitoring → Request Logs with the model, token counts, cost, and latency.
Example curl output:
{"id":"msg_011CdLiqXzSDUMMYvVKFSGnW","choices":[{"finish_reason":"stop","index":0,"message":{"role":"assistant","content":"Hello! 👋 It's nice to meet you. How can I help you today?"}}],"created":1234567890,"model":"claude-haiku-4-5-20251001","object":"chat.completion","usage":{"completion_tokens":23,"prompt_tokens":11,"total_tokens":34}}
Relevant resources
Step 3: put real traffic through the gateway (Dev Console)
The synthetic request in Step 2 proves the plumbing; this step makes the evaluation convincing by running work you actually do — a real coding task or agent run — through the gateway. The provider key you added during onboarding already routes that traffic, so you can point a client at the proxy and go. The two paths below only change whose provider bill the tokens land on; pick one if it applies.
Optional: Bring Your Own Key (per-person billing)
Bring Your Own Key (BYOK) registers a provider API key you already use (OpenAI, Anthropic, and others), so the provider bills your own account instead of the org key from onboarding. Use it when you want each person's spend on their own provider invoice, or a provider the onboarding key does not cover. The gateway measures and attributes the traffic; it does not rebill those tokens. This is not Claude Code passthrough mode; that path is below.
- In the Dev Console, go to Settings → Bring Your Own Key and add credentials for a provider you already use. Credentials are encrypted at rest and never returned.
- Point a coding agent or OpenAI-compatible client at the gateway. Use the proxy endpoint from Step 2 and your Agent Router API key (not the provider key you just added).
# Example: OpenAI-compatible client (proxy endpoint includes /v1)
export OPENAI_BASE_URL=https://proxy.<your-tenant>.tetrate.ai/v1
export OPENAI_API_KEY=YOUR_AGENT_ROUTER_API_KEY
Cursor and similar tools take the same two values in their settings. For Claude Code without a Max/Pro subscription (managed Anthropic credentials on the gateway—not passthrough mode), follow Connect Claude Code → Option A (managed mode): proxy host without /v1, and your Agent Router API key in ANTHROPIC_API_KEY.
- Run a real task with the agent or client.
You should see: the requests in Dev Console Monitoring → Request Logs, attributable to your Agent Router key.
Alternative: Claude Code passthrough mode (Pro or Max subscription)
Passthrough mode lets you keep paying a flat Claude Max or Pro subscription fee while Agent Router Enterprise monitors the traffic—Request Logs, usage, and the Admin Dashboard Spend overview. Anthropic still authenticates you with Claude Code's stored OAuth token; the gateway routes and observes without putting those tokens on Agent Router billing. In the Spend overview, passthrough usage is the theoretical API-rate cost of that traffic if you did not have the subscription—it does not count toward the budget. This is separate from BYOK: you do not paste a Claude subscription into Bring Your Own Key.
- Follow Connect Claude Code → Option B (passthrough mode):
- From a command prompt, type
claude /login - Leave
ANTHROPIC_API_KEYunset - Set
ANTHROPIC_BASE_URLto your proxy host andANTHROPIC_CUSTOM_HEADERSwithx-tars-api-key(your Agent Router API key from Step 2).
- From a command prompt, type
- Start a session (type
claudefrom command promopt) and run a real task.- Confirm with
/statusthat the Anthropic base URL is your proxy host. - In Request Logs, these requests are labeled passthrough.
- Confirm with
You should see: passthrough-labeled requests in Dev Console Monitoring → Request Logs, attributable to your Agent Router key.
Relevant resources
- Use your own provider credentials
- Coding agents and tools
- Connect Claude Code (Option A managed, Option B passthrough)
Step 4: see what the traffic costs (Admin Dashboard)
With real traffic flowing, cost questions move to the Admin Dashboard. Under the sidebar Usage section, start with Analytics to baseline spend. In Step 5 you attach a personal budget under Budgets and read the Spend overview (billed against the ceiling; an optional passthrough line if Claude Code passthrough mode was used). That matches Keep team spend inside a ceiling and See budget exhaustion coming.
Baseline cost in Analytics
Before a ceiling is useful, read the same dimension the budget will use.
- Open the Admin Dashboard (
https://dashboard.<your-tenant>.tetrate.ai) in a web browser. If needed, log in using the account set up in step 1. - Ensure Organization level is selected in the top left corner.
- In the left-hand sidebar, navigate to Usage → Analytics.
- Select tab Cost.
- Use the drop-down box (top right corner) to set a time range that covers the traffic from Step 3 (for example last 24 hours or last 7 days).
- Use the drop-down box directly next to the search box and select Group by Mode to visualize the model usage between managed, BYOK and passthrough request request count, tokens, and estimated cost across keys, models, and providers.
- Once additional users are added Grouping by User or Team provides critical insight into model usage across developers.
Size any monthly ceiling from this baseline: above normal burn, below a number that would be a problem. A first evaluation budget can start tight; you can raise it later.
Write down a monthly projection (a representative day × working days, or a week × about 4.3). That list-price-style figure is the evaluation’s cost signal—comparable to a subscription price or a direct-provider invoice.
You should see: your user row in Cost with tokens and estimated spend you can use to pick a personal ceiling in Step 5.
Relevant resources
- Keep team spend inside a ceiling
- Read the shadow bill (Dev Console view of list-price cost on passthrough traffic)
Step 5: set a budget for yourself (Admin Dashboard)
With a Cost baseline from Step 4, attach a ceiling to your billed spend. Use the One person scope: a monthly USD limit on you alone, independent of any team.
Create a budget
- Open the Admin Dashboard (
https://dashboard.<your-tenant>.tetrate.ai) in a web browser. If needed, log in using the account set up in step 1. - Ensure Organization level is selected in the top left corner.
- In the left-hand sidebar, navigate to Usage → Budgets.
- Click button Add budget.
- Set Scope to One person.
- Select yourself (use search if the list is long).
- Set Spend limit to a given amount in USD (for example, sized from the Analytics Cost baseline in Step 4), or pick a preset ($100, $500, $1,000, …).
- The budget resets at the start of each calendar month (UTC); a mid-month create still applies to spend already in that month.
- Name it (for example
Eval personal cap) and review the summary. - Click button Create budget.
- Verify the new budget is listed in the overview.
Read the Spend overview
- In the left-hand sidebar, navigate to Usage → Budgets.
- Open the budget you created in the previous steps.
- The detail view has configuration on the left (scope, name, spend limit, Active) and Spend overview on the right.
- Read the headline meter.
- billed spend against the ceiling (for example
$36.01 of $100.00 · monthly), plus Used, Remaining, and Days left. - Only billed amounts count toward the limit and drive alerts.
- billed spend against the ceiling (for example
- If you configured Claude Code passthrough mode in Step 3 and sent that traffic, look for passthrough usage (not counted toward budget) under the meter—only .
Claude Code passthrough mode keeps Max/Pro paying the flat subscription fee. The passthrough line is the theoretical cost of those same requests if you did not have the subscription—priced at standard API rates (≈). It is for scale and comparison only; it never draws down the budget. On a team per user budget, each member row can show billed next to passthrough the same way, with the member’s billed amount against their cap.
If Claude Code passthrough mode was not configured, the Spend overview stays simpler: billed against the ceiling, progress bar, Used / Remaining / Days left—no passthrough line.
You should see: the budget under User Budgets, Active, with billed on the meter. A passthrough ≈ total appears only after Claude Code passthrough traffic.
Relevant resources
Step 6: bring in teammates (Admin Dashboard and Dev Console)
A single user proves the mechanism; a small group turns it into decision material. Cost and usage patterns only become comparable when there is more than one person to compare, so this step repeats the personal setup for a handful of the heaviest AI users on the team. Those users produce the most representative spread, and the SSO configured in Step 1 makes onboarding them a matter of a shared link. The payoff is team-level attribution: spend broken down by team, model, and application, which is the evidence a rollout decision rests on.
Create two or more users
- Make sure additional users are created on your IdP (Identity Provider) so they can log in using Single Sign on.
- For Auth0, navigate to https://auth0.com and log in using your credentials.
- In the left-hand navbar, select User Management → Users.
- Click button Create User and select Create via UI.
- Set Connection to Username-Password-Authentication.
- Enter an email for the new user (e.g.
[email protected]) and set a strong password. - Click button Create Another and repeat the process one or more times.
- End by clicking button Create.
Set up for users and teams
- Share the Dev Console URL (
https://router.<your-tenant>.tetrate.ai) with the users you created logins for - Have them sign in with SSO using email address and password, as entered in the previous steps.
- Each user appears in the Admin Dashboard under Directory -> Users, after their first login.
- Each teammate repeats Step 3: BYOK with their provider API key, or Claude Code passthrough mode if they use Claude Max/Pro.
- Assign each team a budget under Usage → Budgets (Whole team or Each teammate), sized from the Analytics baseline in Step 4 and your personal ceiling in Step 5.
You should see: spend comparable across teammates by model and app, with each team's meter drawing down.
Relevant resources
Go deeper (optional)
The fast track leaves behind a working environment and a first set of numbers. The following pages build on it:
- Graded evaluation scenarios: a scored scorecard for a structured, comparable decision.
- Configure SSO: move off the temporary Auth0 tenant to permanent corporate SSO.
- Guides for Developers and Guides for Platform Operators: the full task-by-task reference.