eamchong/pxpipe: cut Fable 5 token usage by rendering text context as images ·
github.com · 1,443 words · saved by 1 readers
cut Fable 5 token usage by rendering text context as images
pxpipe Cut Claude Code's input tokens by rendering bulky context as images — the same system prompt, tool docs, and history, in a fraction of the tokens. An image's token cost is fixed by its pixel dimensions, not by how much text is inside it. Dense content (code, JSON, tool output) packs ~3.1 chars per image-token vs ~1 char per text-token on real Claude Code traffic. pxpipe is a local proxy that exploits the gap: it rewrites the bulky parts of each request into compact PNGs before it leaves your machine. At current Fable list prices that lands as a ~59–70% lower end-to-end bill — but prices
saved by
related reading
- Compare AI Models: Pricing, Context & Benchmarks | OpenRouteropenrouter.ai
- LLM Visualizationbbycroft.net
- Replicate - Run AI with an APIreplicate.com
- AI Model & API Providers Analysis | Artificial Analysisartificialanalysis.ai
- Together AI | The AI Native Cloudtogether.ai
- A Picture is Worth 170 Tokens: How Does GPT-4o Encode Images?oranlooney.com
- Denis Shiryaev | AI & ML Projectsshir-man.com
- Hugging Face – The AI community building the future.huggingface.co
- Parsed | Custom, interpretable AI systems that continuously learnparsed.com
- Prompting best practicesdocs.anthropic.com
- API Overview | OpenAI API Referenceplatform.openai.com
- Rewind.ai - Every AI Tool, Completely Freerewind.ai