> ## Documentation Index
> Fetch the complete documentation index at: https://docs.runbridge.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Usage FAQ

> Common RunBridge AI questions about text and image models, Anthropic Messages, Gemini input, API errors, and account basics.

## Which image API should I use?

Choose [GPT Image](/api/image/openai/images), [Google Nano Banana](/api/image/gemini/gemini-generates-image), or [Grok](/api/image/grok/image-generation). Follow that model family's reference for generation or editing requests.

Use the [Models page](/overview/models) to find a model ID and the [model directory](https://runbridge.ai/models/) to review pricing.

***

## Can I use o-series reasoning models?

Choose an available o-series model ID from the [Models page](/overview/models), then follow the text API reference that matches its request format.

***

## How do I handle API errors?

Use [Handle error codes](/errors/error-codes-handling) to decide whether to fix the request or retry it.

The guide covers `400`, `401`, path and base URL failures, `429`, and timeout responses.

***

## How do I connect a coding tool?

Choose your tool from the [Integrations guides](/integrations), then follow its base URL, API key, and model configuration steps.

***

## How do I send a request to Claude?

Send native Anthropic Messages requests to `POST /v1/messages`. For the Anthropic SDK, set the base URL to `https://api.runbridge.ai`.

See [Anthropic Messages](/api/text/anthropic-messages) for authentication and request fields, or the [Claude API quickstart](/quickstarts/text/claude-api) for a complete example.

***

## Can I use a `.env` file to store API keys?

Store your API key in a local `.env` file or environment variable. Keep that file out of version control and load the key into your application.

For OpenAI-compatible examples, use `https://api.runbridge.ai/v1` as the base URL.

***

## Can I use a Claude model with the OpenAI SDK?

For OpenAI-compatible Chat Completions requests:

1. Keep the same RunBridge AI base URL and API key.
2. Change the `model` value to a Claude model ID from the [Models page](/overview/models).
3. Use the fields documented in [Chat Completions](/api/text/chat) for the selected model.

You do not need to switch SDKs unless you want to move to Anthropic's native Messages format.

***

## How do I send videos to Gemini models?

RunBridge AI does not support uploading a video to a separate Gemini Files API path and reusing that uploaded file later.

For Gemini `generateContent`, send the video directly in the request:

* Use `inlineData` for a local video that you encode as base64.
* Use `fileData.fileUri` for a public HTTPS video URL.

See [Generate content with Gemini](/api/text/gemini-generating-content) for copyable curl examples.

***

## How do I recover a forgotten password?

1. On the login page, click the **"Reset Password"** button.
2. Enter the email address used during registration as prompted.
3. Check your email and follow the instructions in the email to complete the password reset.

<script type="application/ld+json">
  {`
    {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "FAQPage",
        "@id": "https://runbridge.mintlify.site/support/confusion-about-use",
        "url": "https://runbridge.mintlify.site/support/confusion-about-use",
        "name": "Usage FAQ",
        "description": "Common RunBridge AI questions about text and image models, Anthropic Messages, Gemini input, API errors, and account basics.",
        "mainEntity": [
          {
            "@type": "Question",
            "name": "Which image API should I use?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Choose GPT Image, Google Nano Banana, or Grok. Follow that model family's reference for generation or editing requests. Use the Models page to find a model ID and the model directory to review pricing."
            }
          },
          {
            "@type": "Question",
            "name": "Can I use o-series reasoning models?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Choose an available o-series model ID from the Models page, then follow the text API reference that matches its request format."
            }
          },
          {
            "@type": "Question",
            "name": "How do I handle API errors?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Use Handle error codes to decide whether to fix the request or retry it. The guide covers 400, 401, path and base URL failures, 429, and timeout responses."
            }
          },
          {
            "@type": "Question",
            "name": "How do I connect a coding tool?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Choose your tool from the Integrations guides, then follow its base URL, API key, and model configuration steps."
            }
          },
          {
            "@type": "Question",
            "name": "How do I send a request to Claude?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Send native Anthropic Messages requests to POST /v1/messages. For the Anthropic SDK, set the base URL to https://api.runbridge.ai. See Anthropic Messages for authentication and request fields, or the Claude API quickstart for a complete example."
            }
          },
          {
            "@type": "Question",
            "name": "Can I use a .env file to store API keys?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "Store your API key in a local .env file or environment variable. Keep that file out of version control and load the key into your application. For OpenAI-compatible examples, use https://api.runbridge.ai/v1 as the base URL."
            }
          },
          {
            "@type": "Question",
            "name": "Can I use a Claude model with the OpenAI SDK?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "For OpenAI-compatible Chat Completions requests: 1. Keep the same RunBridge AI base URL and API key. 2. Change the model value to a Claude model ID from the Models page. 3. Use the fields documented in Chat Completions for the selected model. You do not need to switch SDKs unless you want to move to Anthropic's native Messages format."
            }
          },
          {
            "@type": "Question",
            "name": "How do I send videos to Gemini models?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "RunBridge AI does not support uploading a video to a separate Gemini Files API path and reusing that uploaded file later. For Gemini generateContent, send the video directly in the request: - Use inlineData for a local video that you encode as base64. - Use fileData.fileUri for a public HTTPS video URL. See Generate content with Gemini for copyable curl examples."
            }
          },
          {
            "@type": "Question",
            "name": "How do I recover a forgotten password?",
            "acceptedAnswer": {
              "@type": "Answer",
              "text": "1. On the login page, click the \"Reset Password\" button. 2. Enter the email address used during registration as prompted. 3. Check your email and follow the instructions in the email to complete the password reset."
            }
          }
        ]
      },
      {
        "@type": "BreadcrumbList",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "RunBridge AI Docs",
            "item": "https://runbridge.mintlify.site/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "Support",
            "item": "https://runbridge.mintlify.site/support/help-center"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "Usage FAQ",
            "item": "https://runbridge.mintlify.site/support/confusion-about-use"
          }
        ]
      }
    ]
    }
    `}
</script>


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.