A low-cost relay that speaks the OpenAI API and forwards straight to official upstreams. Swap a base URL, keep your code, stop juggling four billing accounts.
Text, vision, reasoning and long-context models from every major lab, reachable through a single key and a single quota.
Generation endpoints sit alongside the chat models, so a single account covers your whole pipeline.
Text-to-video and image-to-video generation. Submit a prompt, poll the task, pull the finished clip — no separate vendor contract.
High-fidelity image generation and editing with prompt-level control over composition, style and aspect ratio.
Chat, embeddings, vision, video and images all answer on the same base URL with the same bearer token.
Point any OpenAI-compatible client at the gateway and pass your key.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://www.blitz.mom/v1", api_key="sk-your-key-here", ) resp = client.chat.completions.create( model="claude-sonnet-4-5", # or gpt-4o, gemini-2.5-pro … messages=[{"role": "user", "content": "Hello"}], ) print(resp.choices[0].message.content)
Technical support answers around the clock, in Chinese or English.