Developer Console Quickstart

Ten minutes from sign-in to a first routed AI request. By the end: an API key, a proxy endpoint URL, a working request in at least one language, and a verified entry in Request Logs.

---

info

The screenshots in this guide show a redacted URL. The URL in a production environment resembles router.<custom-name>.tetrate.ai. The Console URL differs based on deployments in production and non-production.

Step 1: sign in

1. Go to the Console URL (for example https://router.poc.tetrate.ai).

   

2. Click Sign In with Corporate SSO. Authentication is handled by the organization's identity provider, so the credentials requested next, commonly a username and password, are the ones that identity provider asks for.

   

3. The Dashboard opens, displaying the proxy endpoint URL and a summary of recent usage activity. Note the proxy endpoint URL; it is needed in Step 3.

Step 2: create an API key

API keys authenticate an application's requests to the gateway. Each key can be assigned its own routing policy (fallback chain, traffic splitting), rate limits, and model scope. This quickstart creates a basic key with default settings.

1. In the sidebar, click API Keys

   

2. Click Add API Key

   

3. Enter a descriptive name for the key (for example my-agent-router-key). Choose a name that identifies the application or workload the key serves; the key value is shown only once, but keys remain identifiable by name in logs and usage reports.

   

4. Click Create key

   

5. Copy the generated key immediately and store it in a secure location (a secrets manager or environment variable). This is the only time the key value is displayed.

caution

API keys grant the bearer the ability to route requests through the gateway and consume AI quota. Store the key securely; do not commit it to source control or include it in logs or error messages.

Step 3: find the proxy endpoint

The proxy endpoint URL is the address an application calls instead of calling AI providers directly. When a request arrives at the proxy, the gateway:

1. Authenticates the request using the API key
2. Applies the routing policy configured for that key (fallback chain, traffic splitting rules)
3. Translates the request format if routing to a different provider (for example OpenAI format to an Anthropic backend)
4. Returns the normalized response, including error normalization if the upstream provider returns an error

The proxy endpoint URL is displayed on the Dashboard and typically looks like:

https://proxy.poc.tetrate.ai/v1

Append the appropriate path for the intended API format:

Format	Path	Description
OpenAI Chat Completions	/v1/chat/completions	Most widely supported format; compatible with all OpenAI-compatible SDKs and agent frameworks
OpenAI Responses	/v1/responses	Newer OpenAI Responses API with a simplified interface
Anthropic Messages	/v1/messages	Anthropic native format for Claude models

For detailed examples of each format including streaming, see Gateway APIs.

Step 4: make the first request

Replace YOUR_API_KEY with the key created in Step 2. All examples below call gpt-4o, but any model name from the Model Catalog can be substituted. To discover models programmatically for the same key, call GET /v1/models; see Models API.

The only difference between calling the gateway and calling a provider directly is the base_url (or the curl URL). All other parameters, response formats, and SDK behaviors are identical.

Asking for a model the project has not been granted returns 404, even if an administrator enabled that model organization-wide. GET /v1/models lists what the key can actually call, so check there rather than against the organization catalog. See Create a project and grant models.

Using curl

curl https://proxy.poc.tetrate.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello, world!"}]
  }'

Using Python

from openai import OpenAI

client = OpenAI(
    base_url="https://proxy.poc.tetrate.ai/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, world!"}]
)

print(response.choices[0].message.content)

Streaming with curl

curl https://proxy.poc.tetrate.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [{"role": "user", "content": "Hello, world!"}],
    "stream": true
  }'

Streaming with Python

from openai import OpenAI

client = OpenAI(
    base_url="https://proxy.poc.tetrate.ai/v1",
    api_key="YOUR_API_KEY"
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Hello, world!"}],
    stream=True
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

Using the playground

The Playground supports interactive testing of model routing without writing any code, useful for evaluating models or verifying routing behavior before integrating into an application.

1. In the sidebar, go to Build > Playground
2. Select a model from the dropdown. The list shows all models currently enabled by the administrator.
3. Type a message and press Send
4. View the response alongside token usage, latency, and the upstream provider that served the request

Step 5: check the request logs

Every request the gateway processes is recorded in Request Logs. This is the primary tool for debugging, auditing, and analyzing cost.

1. Go to Monitoring > Request Logs
2. The request appears with the model name, upstream provider, token counts, estimated cost, and total latency
3. Click any row to view the full request and response payloads, including which provider was selected and whether any fallback attempts were made

Request Logs also display the x-request-id correlation header that the gateway attaches to every response. Use this ID to locate the corresponding span in the OpenTelemetry tracing backend. See Gateway Behavior for details on correlation IDs and the full debugging workflow.

Step 6: view usage analytics

Usage Analytics provides aggregated metrics across all requests. Use it to track consumption trends, compare model costs over time, and understand traffic distribution across API keys.

1. Go to Monitoring > Usage
2. Select a time range (for example Last 24 hours)
3. View breakdowns by model and API key, including total tokens consumed, estimated cost, and request volume

Evaluation checkpoint

• Successfully signed in to the Console
• Created an API key and stored it securely
• Located the proxy endpoint URL on the Dashboard
• Made a successful request via curl, Python, or the Playground
• Confirmed the request appears in Request Logs with provider, latency, and token details
• Reviewed usage analytics for the time period

---

Where to go next

Route requests across providers

Browse the model catalog and configure routing policies.

Improve resilience with fallbacks

Configure fallback chains so the gateway reroutes to a backup provider on errors.