Quick Start

Illustrated guide: sign up, API keys, connectivity checks, and client setup

Quick Start

AutoRouter is a unified AI model gateway compatible with the OpenAI API format. With a single Base URL and API Key, you can call GPT, Claude, Gemini, Kimi, and other mainstream models through one interface—without managing separate accounts for each provider.


Part 1 — Get Started

Follow the steps below in order to register, create an API key, and verify connectivity. Each step includes screenshots and completion checkpoints.

How to Use This Guide

  1. Complete Steps 1 → 6 in order—do not skip ahead.
  2. Compare your results with the expected outcome and completion checkpoint for each step.
  3. Screenshots show the real console UI—follow the highlighted areas.
  4. You only need these three values throughout:
NameDescriptionWhere to Get It
API URL (Base URL)Unified gateway endpointAPI Keys page
API KeyCredential, usually starting with sk-Copy when creating a key
Model nameModel to call, e.g. gpt-5.4Model Plaza

Step 1 — Open the Website

1.1 Open the Homepage

#Action
1Open a browser (Chrome, Edge, etc.)
2Enter the platform URL (e.g. https://autorouter.top)
3Press Enter and wait for the homepage to load

Figure 1-1: Homepage with Sign in and Sign up

Expected result — The page loads normally; Sign in is visible in the header.

Step 2 — Register and Sign In

2.1 Register (if you don't have an account)

#Action
1Click Sign up
2URL changes to /sign-up
3Fill in username/email, password, etc.
4Complete captcha if prompted
5Click Sign up / Submit

Figure 2-1: Sign-up page

Expected result — Success message, or redirect to sign-in / dashboard.

2.2 Sign In (existing account)

#Action
1Click Sign in (usually /sign-in)
2Enter credentials
3Click Sign in

Figure 2-2: Sign-in page

2.3 Open the Dashboard

#Action
1From the homepage, click Dashboard in the header (/dashboard)
2Confirm the left sidebar menu is visible

Figure 2-3: Dashboard entry in header

Step 2 complete — Signed in; sidebar shows API Keys, Playground, etc.

Step 3 — Create an API Key

API keys authenticate all client and code requests.

3.1 Open API Keys

#Action
1In the left sidebar, find the General group
2Click API Keys
3URL changes to /keys

Figure 3-1: API Keys in sidebar

Expected result — Page title is API Keys; Create API Key button in the top-right.

3.2 Create a Key

#Action
1Click Create API Key (top-right)
2Creation form opens on the right

Figure 3-2: Create API Key button

3.3 Fill the Form

#ActionNotes
1Namee.g. daily-chat
2Group / quota / model limitsDefaults are fine for first use
3Click Create / SaveWait for completion

Figure 3-3: Create form

3.4 Copy and Save

#Action
1Find the API Key in the success message or list
2Click Copy or select and copy manually
3Also note the API URL (Base URL)
4Store both in a password manager or secure note

Figure 3-4: Key list with copy button

⚠️ Important: Keys are often shown only once. Do not share publicly; revoke and recreate if leaked.

Step 3 complete — API URL and API Key saved securely.

Step 4 — Verify Connectivity

Use Playground in the console to send a test message.

#Action
1Under Chat, click Playground (/playground)
2Select a model (e.g. gpt-5.4)
3Type Hello and click Send

Figure 4-1: Playground test

Expected result — You receive a text reply from the model.

Step 4 complete — Playground returns an AI response.

Step 5 — Get a Model Name

#Action
1Open Model Plaza in the header or visit Model Plaza
2Search for a model (e.g. gpt-5.4)
3Click the copy icon on the model card

Figure 5-1: Model Plaza search

Step 5 complete — At least one model name recorded.

Step 6 (Optional) — Connect Cherry Studio

This section uses Cherry Studio as an example. Any OpenAI-compatible client works with the same API URL, key, and model name.

6.1 Install the Client

  1. Download from Cherry Studio and install.

6.2 Add a Provider

#Action
1Go to Settings → Model Providers → Add Provider
2Choose OpenAI or OpenAI Compatible

Figure 6-1: Add provider in Cherry Studio

6.3 Enter Connection Details

FieldValue
API URL / Base URLPlatform URL from Step 3 (most clients omit /v1)
API Keysk-... from Step 3
ModelName copied in Step 5

Figure 6-2: API URL, key, and model

6.4 Add Model from Library

#Action
1Open AutoRouter Models, search gpt-5.4
2Click + to add the model

Figure 6-2-1: Search and add model

Expected resultgpt-5.4 appears in the model list.

6.5 Add Model Manually (if not found)

#Action
1Click + or Add Model next to the model area
2Set Model ID / Name / Group to gpt-5.4 (or your copied name)
3Confirm Add Model

Figure 6-2-2: Manual add

6.6 Test Chat

After saving, go to Home, select the model, send Hello, and expect a reply.

Figure 6-3: Cherry Studio chat test

Step 6 complete — Cherry Studio (or another client) chats successfully.


Part 2 — Developer Integration

After the quick start above, use these examples to integrate via SDK or CLI. The platform is OpenAI-compatible—replace base_url and api_key with your values.

2.1 Prerequisites

ParameterDescription
Base URLhttps://autorouter.top/v1 (SDKs usually include /v1; curl paths below already include it)
API Keysk-... from Step 3
Model nameFrom Step 5, or query via 2.4

2.2 Verify with curl

curl https://autorouter.top/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-yourAPIKey" \
  -d '{
    "model": "gpt-5.4",
    "messages": [
      {"role": "user", "content": "Hello, introduce yourself"}
    ]
  }'

2.3 Python SDK

from openai import OpenAI

client = OpenAI(
    base_url="https://autorouter.top/v1",
    api_key="sk-yourAPIKey",
)

response = client.chat.completions.create(
    model="gpt-5.4",
    messages=[
        {"role": "user", "content": "Hello, introduce yourself"},
    ],
)

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

2.4 List Available Models

curl https://autorouter.top/v1/models \
  -H "Authorization: Bearer sk-yourAPIKey"

The id field in the response is the model parameter for API calls.


Part 3 — Connect Your Tools

Any OpenAI-compatible client needs only these three values:

3.1 Three Essentials

ParameterValue
API URL (Base URL)https://autorouter.top
API KeyKey created in the console
Model nameFrom /v1/models or Model Plaza

3.2 Claude Code / Codex CLI

For CLI coding assistants, set:

export OPENAI_API_KEY="sk-yourAPIKey"
export OPENAI_BASE_URL="https://autorouter.top/v1"

3.3 OpenClaw

Add to ~/.openclaw/openclaw.json:

{
  "models": {
    "mode": "merge",
    "providers": {
      "autorouter": {
        "baseUrl": "https://autorouter.top/v1",
        "apiKey": "sk-yourAPIKey",
        "api": "openai-completions",
        "models": [
          { "id": "gpt-5.4", "name": "GPT-5.4" }
        ]
      }
    }
  },
  "agents": {
    "defaults": {
      "model": {
        "primary": "autorouter/gpt-5.4"
      }
    }
  }
}

3.4 Other OpenAI-Compatible Tools

  • API URL / Base URLhttps://autorouter.top
  • API Key → Your console key
  • Model name → From /v1/models

More verified app guides: Agent Tools.


Part 4 — API Overview

APIEndpointDescription
Chat completionsPOST /v1/chat/completionsMulti-turn chat, streaming, tool calling, structured output
Text completionsPOST /v1/completionsLegacy completion API
Image generationPOST /v1/images/generationsAI image generation
Video generationPOST /v1/videosAI video generation
Model listGET /v1/modelsList available models

Full reference: API Docs.


Part 5 — Troubleshooting

IssueSuggestion
Can't find API KeysEnsure you're signed in; open API Keys directly
401 / invalid keyCopy the full key; check expiry or disabled status
Insufficient quotaTop up wallet or contact admin
Model not foundCopy the correct name from Model Plaza
Should URL include /v1?Chat clients usually omit it; SDKs usually include it

Part 6 — More Help

NeedResource
Parameters, error codesAPI Docs
More client integrationsAgent Tools
Deployment, billingContact your site administrator

On this page