The same 50-call agent run on opus 5.5 costs $0.74 or $12.50.
The difference is one timestamp in the system prompt a 50k-token prompt, resent on every call: no caching: 50 × $0.20 = $10.00 caching on: one $0.25 write, then 49 reads at $0.01 = $0.74 caching on, "current
Sepp is now driving in the beer barrel 🍺 Suppa Lederhosn Karts
12 karts, pretzel hunters in the steel ditch & time jump at 142 km/h ⚡ A joint work of Blender, Unreal, ElevenLabs, Opus 5, Opus 5.5, Astra 6 & GLM 5.3. Play:
How far did Claude Code (Opus 5.5) travel?☺️
What Claude Code did: ・Cut design and prompts ・Created with MiniMax H3 (174 frames) and checked all frames ・Retake, temporary assembly, effects, export What I did: ・Character and project (I want to make a PV of a handsome idol)
Claude Opus 5.5 and GPT-6 Sol are now live in Draftbit — the new defaults for Claude Code and Codex.
🚀 ⚡ Opus 5.5: 40% cheaper to run and 30%+ faster than Opus 5 (savings vary by task) 🎯 GPT-6 Sol: about half the factual mistakes of GPT-5.6 Sol 💸 GPT-6 Luna: beats GPT-5.6
You have reached the end of the archive
All of Claude Opus 5