Fable's High Cost Drives Users to Prepare Better Context
dbreunig · x · 2026-07-04
dbreunig shared thoughts on using Anthropic's new model Fable: first, it is expensive but of extremely high quality; second, precisely because of the high cost, users put more effort into preparing the environment, reference materials, and context to ensure value for money; third, he accidentally found that Opus is actually more suitable for certain tasks. Overall, it reflects how high-priced models are changing usage patterns and workflows.
Related event: Anthropic's Fable Model Praised for Quality, Criticized for API Cost(2 posts)→
More from Models
- OpenAI ships GPT-6.1 Terra; Brockman says its computer use now beats his own speed — gdb · 2026-10-27
- Kimi K3.1 Pro regresses on Debate Benchmark while DeepSeek 1017 gains at lower cost — teortaxesTex · 2026-10-27
- 4 Hours of LLM Startup Research Produced a Convincing but Nonsense Product Thesis — annetgriffin · 2026-10-27
- Dev argues Claude burns far more tokens than GPT models for the same coding work — haider1 · 2026-10-27
- MiniMax matches Claude Opus 4.5 in non-benchmaxxed evals, users report — teortaxesTex · 2026-10-27
- Real-world math: GPT-6.1 Terra's half price is offset by 2-3x token usage, costing more than Sol — lordpuddingcup · 2026-10-27