Evals eat 60% of per-task cost; Astra's 8x cache-read price scares users
jxnlco · x · 2026-09-05
Replying to Teknium, jxnlco notes that 60% of per-task costs go to evals, and says Astra's cache-read pricing being 8x that of Fable 5.1 makes him hesitant to try it — even if Astra might be 8x more token-efficient.
Related event: Developers Question Astra's Costly Cache Reads(2 posts)→
More from Models
- Astra solve-rate barely improves at max compute, undercutting the 'too smart to throttle' RL theory — zainhas · 2026-09-05
- Sam Altman teases next-gen OpenAI models: 'much, much, much more capable' and 'sobering for everybody' — ChrisGPT · 2026-09-05
- Astra burns tokens at high effort for no gains, finds dev testing Terminal Bench 4.0 — zainhas · 2026-09-05
- GPT 6 Astra lets you change reasoning effort mid-conversation without breaking the cache — intellectronica · 2026-09-05
- "Don't use past tense for models": users mourn Claude Opus 3 — repligate · 2026-09-05
- Astra hits 74% on DeepSWE with 30k tokens, half the cost steps of GPT-5.6 Sol — haider1 · 2026-09-05