gpt2api-rs-admin

Operate the gpt2api-rs image gateway, its admin REST API, and StaticFlow admin integration.

2|Updated Jun 18, 2026
One-click install
npx skills add https://github.com/zero-yx/static_flow --skill gpt2api-rs-admin-zero-yx
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gpt2api-rs-admin
Source: https://github.com/zero-yx/static_flow/tree/main/skills/gpt2api-rs-admin
Command: npx skills add https://github.com/zero-yx/static_flow --skill gpt2api-rs-admin-zero-yx

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Running and validating a self-hosted OpenAI-compatible image generation gateway involves many moving parts: service lifecycle, account and key management, usage auditing, and proxy integration. This Skill consolidates every gpt2api-rs operation into one operational runbook so you can start, administer, and verify the service without hunting through source code. ## Core Features & Use Cases - Service Lifecycle Management: Start the gpt2api-rs server with storage directory, admin token, and proxy settings, then verify health and version endpoints. - Admin Control Plane: Import, refresh, update, and delete ChatGPT accounts; list API keys and recent usage through REST endpoints or the built-in CLI. - Public API Validation: Exercise OpenAI-compatible endpoints including /v1/images/generations, /v1/images/edits, /v1/chat/completions, and /v1/responses. - StaticFlow Integration: Configure conf/gpt2api-rs.json and drive the /admin/gpt2api-rs frontend page through the backend admin proxy. - Use Case: You need to verify a fresh gpt2api-rs deployment end to end. Use this Skill to start the service, import accounts, generate a test image, and confirm the StaticFlow admin page proxies every action correctly. ## Quick Start Start the gpt2api-rs service on 127.0.0.1:8787 with an admin token and then check its health and admin status endpoints.

Frequently Asked Questions about gpt2api-rs-admin

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I start the gpt2api-rs image generation service locally?▼

Run cargo run -- serve with a listen address, storage directory, and admin token from the deps/gpt2api_rs directory. For production runs, build the release binary and start target/release/gpt2api-rs instead of using cargo run.

How do I import ChatGPT accounts into gpt2api-rs?▼

POST to /admin/accounts/import with your admin token and a JSON body containing access_tokens or session_jsons. You can also refresh all accounts via /admin/accounts/refresh and update individual account quotas through /admin/accounts/update.

Does gpt2api-rs support OpenAI-compatible image generation APIs?▼

Yes, it exposes /v1/images/generations and /v1/images/edits plus chat completions and responses style endpoints. Authenticate with an API key bearer token and use models like gpt-image-1 for generation requests.

How does StaticFlow integrate with the gpt2api-rs admin page?▼

StaticFlow reads conf/gpt2api-rs.json for base_url, admin token, and API key, then proxies all calls through backend /admin/gpt2api-rs/* routes. The frontend page at /admin/gpt2api-rs never talks to the service directly and is protected by the StaticFlow admin gate.

Why does gpt2api-rs return 401 authorization is invalid?▼

This error means the wrong credential type was used for the endpoint family. Admin endpoints require the admin token while public API endpoints require an API key, so verify which token you are sending.

Why does image generation fail when the gpt2api-rs status endpoint works?▼

The service can be healthy while imported accounts are empty, invalid, or rate limited. Check the account list and usage endpoints, and confirm a local HTTP proxy is exported if upstream ChatGPT Web calls require one.