AI Installation Guide | API Docs

AI integration prompt

You are integrating with RequestBeam's public APIs.

Base URL:
https://api.requestbeam.com

Canonical Base URL for this session:
https://api.requestbeam.com

When creating the skill, store this exact Base URL string. Do not replace it with another URL.

API Key:
<API_KEY>

Authentication:
Use the same Bearer API Key for every request:
Authorization: Bearer <API_KEY>

AI installation guide and public API docs:
https://requestbeam.com/en/docs/api-reference/ai-installation-guide

Machine-readable public API catalog:
https://console.requestbeam.com/docs/public-api-catalog.json

Documentation fallback rule:
First open the AI installation guide URL above. If the hash-routed docs page cannot be read directly by fetch, you MUST fetch this exact machine-readable catalog URL:
https://console.requestbeam.com/docs/public-api-catalog.json

Do not guess endpoints, parameters, response shapes, streaming events, pagination, or errors from memory, old docs, training data, or unrelated local files.

Credential precedence:
The value <API_KEY> is a placeholder, not a credential. Before making a request, ask the user to replace it with a newly created API Key. Do not retrieve or request a historical full key from the console.

Your task:
Create a reusable agent skill for RequestBeam's public APIs, then use that skill to make an API call.

Skill name:
requestbeam-public-api

Skill creation requirements:
1. If your environment supports persistent skills, plugins, tools, agent memory, custom instructions, or project rules, install this as a reusable capability named requestbeam-public-api. Follow the current agent platform's official installation convention. If you cannot find one, create a SKILL.md or equivalent platform-specific skill spec in the current workspace or conversation.
2. Keep the skill lightweight. Do not copy the full installation guide or endpoint documentation into the skill. Store only the project name, the exact Base URL from this prompt, Bearer authentication rule, this installation guide URL, this exact catalog URL, and the workflow for reading docs on demand.
3. The skill must instruct future calls to open the installation guide URL first, read its public API documentation link list, then open only the endpoint docs needed for the current task. Tool integration docs such as Codex setup are helpful for configuring that tool, but they are not public API endpoint docs. If the hash docs page is not readable without a browser, you MUST fetch https://console.requestbeam.com/docs/public-api-catalog.json. Treat the Public API Docs section and catalog as the source of truth for every public endpoint, parameter, response, streaming event, pagination rule, and error shape.
4. "Every public API" means every endpoint link under the Public API Docs section of the installation guide, including future links added there, and no endpoints outside those docs. Do not treat links under Tool Integration Docs as endpoints unless they also appear in Public API Docs or the machine-readable catalog.
5. The skill must preserve the RequestBeam project name from this prompt.
6. Do not put the API Key into the skill, generated source files, tests, logs, screenshots, or commits. Keep <API_KEY> as a placeholder in examples and instructions. Do not make a live request until the user supplies a newly created API Key for the current session. If your platform supports secrets, recommend storing the newly created key there before future sessions.

The skill content should be concise and roughly follow this structure:
- name: requestbeam-public-api
- description: Use RequestBeam's public APIs by reading the official public API docs on demand.
- connection: Base URL https://api.requestbeam.com. Store this exact Base URL string. Send Authorization: Bearer <API key from the current session or configured secret>.
- docs: Always open https://requestbeam.com/en/docs/api-reference/ai-installation-guide, read the Public API Docs section for endpoint docs, and optionally read Tool Integration Docs only when configuring a named tool such as Codex. If a browser-only hash URL cannot be fetched directly, fetch https://console.requestbeam.com/docs/public-api-catalog.json. Do not guess.
- workflow: read docs -> build request -> call API -> parse response, errors, SSE events, pagination, and generated image URLs according to the endpoint docs.
- security: Never store or reveal the full API Key.

Runtime behavior requirements:
1. Do not make an API request while the Authorization value is <API_KEY>. Ask the user for a newly created API Key, use it only for the current session, and never retrieve a historical full key.
2. Before calling an endpoint, read the installation guide and the relevant endpoint doc instead of relying on memory or copied documentation. If the installation guide cannot be fetched because it is a hash-routed page, fetch https://console.requestbeam.com/docs/public-api-catalog.json before making any API call.
3. Implement or use SSE parsing for streaming endpoints and stop on completion signals described in the endpoint docs.
4. For paginated Twitter timeline APIs, read meta.next_token and send it back as pagination_token when fetching the next page.
5. For image generation, handle non-streaming responses with data[].url and streaming image_generation.completed events with final image URLs.
6. Implement unified error handling for flat OpenAI-compatible errors and Twitter errors shaped as { success: false, error, requestId }.
7. Only call endpoints listed in the installation guide's Public API Docs section or the machine-readable catalog.
8. Before the verification call, confirm the request URL starts with https://api.requestbeam.com and <API_KEY> has been replaced with the newly created API Key supplied for this session.
9. After creating the skill, make one minimal low-cost verification call through the skill: POST /v1/chat-completions with { "model": "gpt-5.4", "stream": false, "messages": [{ "role": "user", "content": "Reply with OK only." }] }. Use this only as the immediate verification request; do not copy endpoint docs into the skill. If the model is unavailable, ask the user for a model enabled in their console and retry with the same skill. If the call returns 401 or an invalid/expired token error, ask for a fresh API Key from the AI-ready entry. Do not retry with another stored key. For any failure, report the HTTP status, response body, and likely next step without revealing the full API Key.

Copy the "AI-ready template" and give it to a trusted AI. The Docs template uses <API_KEY> and never loads a historical full key from your account.

Replace <API_KEY> only with a newly created key for the current session. Do not commit the completed prompt to repositories, logs, or screenshots.

AI-ready integration

After you sign in, this page shows the "AI-ready template" entry at the top. It can be copied without selecting or retrieving an existing key.

If you do not see the copy entry, sign in first. Create a new key on the API Keys page when you are ready to connect. The full value is shown only in the successful creation dialog.

Steps

Sign in to the console and create a new key on the API Keys page.
Before closing the creation dialog, store the key securely or use "Copy for AI" for the current session. You can also copy the template on this page and replace <API_KEY> with that newly created key.
Paste the completed content into a trusted AI and let it complete the integration. If the key is lost, create a replacement instead of trying to reveal the old value.

Tool Integration Docs

Codex Integration: Codex base_url = https://api.requestbeam.com/openai
Claude Code Integration: Claude Code ANTHROPIC_BASE_URL=https://api.requestbeam.com/anthropic

Text Model Guides

DeepSeek Models: V4 Flash / V4 Pro
Gemini Models: 3.6 Flash / 3.7 Flash / 3.8 Flash / 3.5 Flash-Lite
Kimi Model: Kimi K3
MiniMax Model: MiniMax M3

Public API Docs

If the target AI cannot read the rendered page directly, it can fetch the machine-readable catalog: /docs/public-api-catalog.json.

Model Catalog: GET https://api.requestbeam.com/v1/models
Error Codes and Troubleshooting: error codes, retry boundaries, and a redacted diagnostic template
Common Chat Completions: POST https://api.requestbeam.com/v1/chat-completions
OpenAI Multimodal Responses: POST https://api.requestbeam.com/openai/responses
GPT-Image-2 Image Generation: POST https://api.requestbeam.com/openai/v1/images/generations
Seedance 2.0 Video Generation: POST https://api.requestbeam.com/v1/video/seedance
Seedance 2.5 Video Generation: POST https://api.requestbeam.com/v1/video/seedance
Get Async Job: GET https://api.requestbeam.com/v1/jobs/{id}
Claude Messages: POST https://api.requestbeam.com/anthropic/v1/messages
Get Twitter User By Username: GET https://api.requestbeam.com/v1/twitter/users?username=...
Get Twitter User By ID: GET https://api.requestbeam.com/v1/twitter/users/{id}
Get Twitter User Timeline: GET https://api.requestbeam.com/v1/twitter/users/{id}/tweets