DeepSeek V4.1 Flash Hits 1T Tokens in 24 Hours on OpenRouter, Poised to Set Paid-Launch Record
Key Info
DeepSeek V4.1 Flash processed 1 trillion tokens in its first 24 hours on OpenRouter, with 90% of those being cache reads priced at roughly $0.006/M — about 5x cheaper than comparable models such as GLM-5.3 Flash. It is on pace for the biggest 48-hour launch of any paid model at ~2.8T tokens.
Highlights
- Strong early adoption: 1T tokens in 24 hours, projected to hit ~2.8T in the first 48 hours.
- Cost efficiency stands out: cache reads dominate traffic and are priced 5x lower than comparable models.
- Signals growing demand for high-performance, low-cost LLM inference on unified API platforms.