Open-source tool pxpipe hides text in PNGs to cut Claude Code and Fable 5 token costs up to 70%
The open-source tool pxpipe converts long text prompts for Claude Code into compact PNGs, exploiting the fact that Anthropic charges for images by pixel size, not text content. Developer Steven Chong reports cost savings of 59 to 70 percent, at the price of accuracy and speed.
Text costs roughly one token per character, but images cost a fixed number of tokens based on their pixel dimensions, no matter how much text they contain. Render dense content like code or JSON as an image, and you can pack about 3.1 characters into every image token. pxpipe puts this into practice as a local proxy. It intercepts requests to Claude Code and renders the bulky, static parts as images, including system prompts, tool documentation, and older chat history. Recent messages and model outputs pass through as normal text. The image below shows what the model actually sees: Around 48,000 characters of system prompt and tool documentation get squeezed onto a single densely packed PNG page. As text, that would cost about 25,000 tokens. As an image, it’s roughly 2,700. According to developer Steven Chong, total savings average 59 to 70 percent. In one Fable 5 demo, session costs dropped from $42.21 to $6.06. If this somewhat exotic trick catches on, AI companies could respond by raising image processing prices. The approach has downsides. It’s lossy and exact strings like hashes can come back garbled when read from images. Processing is also slower since the model has to run the rendered images through a vision encoder instead of reading text directly. By default, pxpipe supports Claude Fable 5 and GPT 5.6. Benchmarks and evaluations are documented in the repository.
