Token Optimization
Practice of reducing the number of tokens sent to and received from an LLM without losing task quality. Includes prompt caching, message pruning, context window management, and structured output.
Related coverage
- CodeGraph pre-indexed knowledge graph cuts agent tool calls by ninety-four percent
- How Cursor's custom fine-tuned model accelerates multi-file code editing
- Optimizing context costs for twenty-four times agent token usage growth by twenty-thirty
- Pre-Indexed Codebase Knowledge Graphs Slashes AI Agent Tool Calls by Ninety-Four Percent
- Training highly token-faithful coding agents without code modification using NVIDIA's Polar framework
- CodeGraph Slashes AI Coding Agent Tool Calls by Ninety Four Percent Using Pre-Indexed Knowledge
- Anthropic files for initial public offering following near one-trillion dollar valuation milestone
- Anthropic secures $65 billion in Series H funding, reaching a $965 billion valuation
- Building lightweight Web scraping agents for alternative protocols beyond HTTPS
- Hermes Agent Integrates Dynamic Tool Search to Reduce Context Window Token Spend
- CodeGraph pre-indexed knowledge graph cuts AI agent tool calls by ninety-four percent
- Cursor Launches Official Plugins to Enable Modular Customization of AI Coding Environments