Connect OpenClaw, 小龙虾, Hermes, and Other AI Agents with a Single Prompt | Top Image Generation Model GPT-IMAGE-2 from as Low as RMB 0.03 per Image

Register and subscribe, create a token, let your Agent learn the API documentation, then send a single prompt to connect GPT-IMAGE-2 image generation capabilities to mainstream AI Agents such as OpenClaw, 小龙虾, Hermes, Codex, and Claude Code.

This article explains how to subscribe to the GPT-IMAGE-2 image generation package via **superaiapi.com**, then connect the service to mainstream AI Agents such as OpenClaw, 小龙虾, and Hermes with a single prompt, enabling low-cost, high-quality image generation from as low as RMB 0.03 per image.

1. Registration, Subscription, and Token Configuration

Step 1: Register and Open Wallet Management

Go to https://superaiapi.com/, register and log in, then click the upper-right corner to enter the Wallet Management page.

Step 2: Subscribe to the GPT-IMAGE-2 Image Generation Package

On the Wallet Management page, find the Subscribe Package button to the right of Credit Top-up, select the gpt-image-2 image generation package, and complete the payment.

Step 3: Create a Token

After subscribing, go to the Token Management page and click Add Token.

**Note:** The token name can be anything you like, but the **token group must be set to “gpt-image”**; otherwise, you will not be able to call the image generation service later.

Step 4: Verify the Image Generation Service

Find the Drawing https://superaiapi.com/console/drawing entry on the left side of the Personal Center, then enter the drawing workspace to test it. If an image can be generated successfully, the configuration has taken effect.

2. Connecting to an AI Agent

Once the image generation service is ready, you only need one prompt to connect it to any AI Agent (Hermes, OpenClaw, 小龙虾, Codex, Claude Code, etc.; the principle is the same).

Step 5: Let the Agent Learn the API Documentation

Open the superaiapi.com API documentation site https://superai.apifox.cn/, find the following two documents, and copy their links:

📄 gpt-image-2 Create Async Image Task https://superai.apifox.cn/api-453818652

📄 gpt-image-2 Create Async Image Editing Task https://superai.apifox.cn/api-453818653

Send the links to your AI Agent and include the following prompt:

https://superai.apifox.cn/api-453818652
https://superai.apifox.cn/api-453818653
Study these two documents and organize them into an image generation skill.

After the Agent finishes learning and organizing the documentation, it will ask you to provide an API Key. Return to the superaiapi.com Token Management page, copy the API Key you just created, and send it to the Agent.

3. Text-to-Image in Practice

After the configuration is complete, go to the Prompt Library https://superaiapi.com/console/drawing/gallery and choose a reference prompt.

Example: Generating a Travel Poster

Copy the following template from the Prompt Library, replace [country] with the target country, and send it to the Agent:

Create a stylized travel poster / graphic collage for [country]. The main subject should be a stylish international tourist visiting [country], clearly presented as a traveler and not a local resident. Show the tourist wearing modern travel fashion, with details such as a camera, backpack, sunglasses, map, or suitcase, exploring the culture and atmosphere of [country]. Place the tourist in a dynamic composition surrounded by iconic architecture, streets, landscapes, landmarks, transportation, food, signage, and cultural elements associated with [country]. Blend realistic character detail with a graphic collage background made of layered paper textures, torn poster edges, sticker elements, halftone dots, editorial typography, and bold geometric shapes. Include authentic visual motifs from [country], but keep the tourist's appearance and styling globally fashionable and clearly foreign to the setting. Add a large readable headline: "LOST IN [country]". Modern, artistic, premium editorial travel poster aesthetic, balanced layout, print-worthy composition.

The Agent will automatically call your subscribed package to generate the image:

4. Image-to-Image in Practice

Example: Custom Protagonist Poster

First, send a photo to your Agent, then attach the prompt: