​

RunBridge AI getting started guide

​

Review your account balance

After you sign in, open the Wallet page to review your balance and account credits before sending a request.

---

​

How to top up?

1. After you sign in, enter the amount you want to add on the Wallet page.
2. Follow the checkout instructions to complete the payment.

---

​

Which large language model APIs are available?

Find model availability and pricing in the model directory. Use the Models page to get model IDs for requests.

---

​

How to get an API key?

1. After you sign in, open the API key page and click Create API Key.
2. Enter a name, choose the quota setting, and click Create.
3. Copy the key and store it in your environment.

---

​

How to switch between models?

Choose a model ID from the Models page. Enter the complete ID in the field or URL segment shown by the matching text or image reference.

---

---

​

Is billing per usage or monthly?

Check the model’s pricing and billing unit in the model directory. For token-based text requests, use the model’s input and output token prices. For image requests, follow the selected model’s token, task, or image pricing. Use Estimate request cost to plan a request budget, then compare it with actual usage.

---

​

Choose a base URL

Use the base URL for your SDK’s request format: SDKs append the operation path. For direct HTTP requests, use the complete URL in the API reference. See Change the base URL for configuration examples.

---

​

Choose a Claude model

Select an available Claude Sonnet, Haiku, or Opus model ID from the Models page.

---

​

Which URL should I use for Anthropic Claude?

For the Anthropic SDK, use https://api.runbridge.ai as the base URL. It sends Messages requests to /v1/messages. Follow the Anthropic Messages reference for authentication and request fields. If you call Claude through OpenAI-compatible Chat Completions, use https://api.runbridge.ai/v1 as the SDK base URL.

---

​

How to check how many Tokens were consumed in a call?

1. Go to the “Logs” page.
2. Click on a single log entry to expand detailed call information and view the calculation formula and Token consumption:
   • Prompt: Understood as the user input.
   • Completion: Understood as the AI’s response.

---

​

What do “prompt” and “completion” refer to?

• Prompt: Refers to the content input by the user.
• Completion: Refers to the content output by the AI.

---

​

What happens if my balance becomes negative?

When your balance is very low, if the cost of your last call exceeds your remaining balance, your balance will show as negative. Top up your balance before sending another request.