Fun fact: avg turns per task in Cline went from 26 in March → 50 in August. Nearly 2x in 5 months.
We’re trusting agents with bigger jobs faster than ever before.
This wouldn’t be possible without cost efficiencies like with the latest DeepSeek models 💪
DeepSeek V4.1-Flash beats V4-Pro 0813 less than a month after its release.
And it's $0.30/$1.20 per 1M input/output. That's roughly:
- 1/20th cost of Opus 5
- 1/17th cost of GPT-5.6 Sol
- 1/12th cost of Kimi K3
...while beating all three on Terminal-Bench.