#cost
Wiki 6
- A $500 RL Fine-Tune That Beat the Frontier A $500 GRPO fine-tune of a 9B open model beat every frontier config on catalog review, 68× cheaper
- Code Mode Token Savings One script against 26 tool calls on agent-swarm's own production data — a self-measured 99.2% cut
- DeepSeek V4 Flash 0731 scores 50 on the Artificial Analysis Intelligence Index, 10 points above previous DeepSeek V4 Flash Artificial Analysis puts DeepSeek V4 Flash 0731 at 50, one point under GPT-5.6 Luna for ~60% less per task and on the cost Pareto frontier
- LLMs: Intelligence vs. Cost Guido Imperiale replots Artificial Analysis's intelligence-vs-cost chart on a linear axis with OpenRouter and local-electricity prices
- Portal by Spotify Cut Claude Code Token Usage by 90% Spotify PM routes Claude Code's bulk file reads and boilerplate to a cheaper model via hooks; the 90% covers bulk reads, not total usage
- Prompt Caching in Agents How KV-cache reuse sets the cost, latency and tool design of a coding agent, and what Pi shows
Toolbox 1
- tare Claude Code skill and three Python scripts that read local session logs to explain where usage went and why a limit was hit