Paritok
Compresses tools, files, and history for AI coding agents, enabling longer sessions and lower costs.
Paritok acts as a compression gateway for AI coding agents, sitting between the agent and the LLM. It non-destructively compresses tools, files, and conversation history on the fly. This allows for significantly longer coding sessions and reduces LLM token costs. It's powered by an open-source, code-native 4B compression model.
Freemium
0.30
How to use Paritok?
Integrate Paritok by setting a single environment variable. Your AI coding agent sends tool schemas, files, and history as usual. Paritok then filters and compresses this data before sending it to the LLM. The LLM's response is returned unchanged. For self-hosting, download the gateway and 4B model from GitHub. For hosted use, connect to the provided endpoint.
Paritok 's Core Features
Paritok 's Use Cases
Paritok 's Pricing
Self-host
Free
Deploy the gateway and 4B model on your own hardware. Apache-2.0 license.
Hosted GPU
0.30
Managed endpoint on Paritok's GPUs. Free until Oct 1st. Priced per 1M tokens.
Paritok 's FAQ
Most impacted jobs
Software Engineer
AI Developer
Machine Learning Engineer
Data Scientist
Prompt Engineer
DevOps Engineer
