Model Releases
Many assume that agent spend goes toward output tokens. When we ran DeepSWE on Astra vs. DeepSeek V4.1-Flash, input tokens outnumbered outpu…
Many assume that agent spend goes toward output tokens. When we ran DeepSWE on Astra vs. DeepSeek V4.1-Flash, input tokens outnumbered output 174 to 1. 99.6% were cache hits. Those hits are 60% of the
Many assume that agent spend goes toward output tokens. When we ran DeepSWE on Astra vs. DeepSeek V4.1-Flash, input tokens outnumbered output 174 to 1. 99.6% were cache hits. Those hits are 60% of the bill. Net result? Same quality. 0.43/task vs 6.52. https://x.com/i/article/2099896422330216450
Related
- DeepSeek V4 Pro costs 1.74/1M input tokens and 3.48/1M output tokens, while V4 Flash costs 0.14/1M and 0.28/1M; both models are the cheapest in their class (Simon Willison/Simon Willison's Weblog)
- Artificial Analysis: DeepSeek's V4-Flash costs 0.14/1M input and 0.28/1M output tokens, or 0.03 per test, far below Kimi K3's 0.86 and GPT-5.6 Sol's $1.86 (Eduardo Baptista/Reuters)
- DeepSeek says it plans to implement substantial price increases across its services; V4 Flash currently costs 0.14/1M input and 0.28/1M output tokens (Bloomberg)
Source: Fireworks AI (X) | 2026-09-15