Terra and Sonnet cost $1.22 vs. $4.03 in the same lead-report test
samuelcolvin · x · 2026-07-24
A follow-up screenshot adds the raw usage numbers behind the Terra vs. Sonnet comparison.
Cost and usage
- gpt-5.6-terra: 752,254 input tokens, 17,884 output tokens, 39 tok/s, $1.22.
- claude-sonnet-5: 1,834,569 input tokens, 36,172 output tokens, 43 tok/s, $4.03.
It reinforces the earlier claim that Terra delivered the better lead report while spending far less.
Related event: Terra Outperforms Sonnet in Lead Classification at Lower Cost(3 posts)→
More from Models
- Kimi's base-model struggles vs DeepSeek's compute ownership advantage — teortaxesTex · 2026-09-11
- Teortaxes: Kimi stuck serving old K2 base as K2.8 rumored post-trained variant; DeepSeek's compute moat — teortaxesTex · 2026-09-11
- Qwen core dev teases 'v4p back? k3-0.2?' in cryptic model hint — JustinLin610 · 2026-09-11
- Frontier model weights are near-impossible to steal or self-replicate, argues Bindu Reddy vs AI doomers — bindureddy · 2026-09-11
- Why won't Google open source its STT models while startups ship SOTA open voice models? — techtotechbytechy · 2026-09-11
- User Praises DeepSeek's Model as Surprisingly Fast and Good in Hands-on Test — MaziyarPanahi · 2026-09-11