
What happened
OpenRouter's weekly token consumption surged more than 25,000 percent since January 2025, from 0.5 trillion to 126.2 trillion tokens, according to the platform's data.
Why it matters
This suggests inflated token metrics rather than a matching jump in actual usage or business value, as reasoning models and unoptimized agents generate massive 'thinking' tokens.
What to watch
The surge's implications hinge on whether token counts reflect true adoption; meanwhile, Chinese models like Kimi, GLM, and DeepSeek show monthly spending up tenfold in 2026, though from a smaller base.
WHO IT HITSFor business decision-makers evaluating AI adoption, the OpenRouter data highlights that token consumption metrics may overstate actual usage and value, especially when reasoning models and unoptimized agents inflate counts. This could affect investment and strategy choices in AI tools.
Summaries like this, every morning.
OpenRouter's data shows a dramatic rise in token consumption, but this trend is tied to how modern AI models operate. Reasoning models, which generate extensive 'thinking' tokens before answering, can inflate counts without a proportional increase in user activity. Similarly, unoptimized agentic systems may consume tokens inefficiently, further skewing the numbers.
The article notes that OpenAI's GPT 5.6 Luna recently dominated token consumption, but this may simply mean it generates more tokens per prompt, not that more people are using it. Meanwhile, Chinese models like Kimi, GLM, and DeepSeek are growing rapidly in spending, albeit from a smaller base.
The key takeaway is that token metrics alone may not reliably indicate AI adoption or business value. The real test is whether these consumption trends translate into tangible outcomes, which remains uncertain as the industry continues to evolve.
Pick your industry and the AI tools you use, and get news related to your work every day.
Free · 30 seconds with Google · unsubscribe anytimeWhat is AIToday? →
Ask AI anything about this article. The AI reads this article, earlier AIToday articles, and Wikipedia, and cites its sources. Q&As are published on this page for other readers too.
ResearchAndMarkets.com added its "Asset Tracking Artificial Intelligence (AI) Market Global Report 2026," proj…

T-Mobile announced new AI-powered intelligence and resilience capabilities for its 5G network, aiming to make…

Copper futures sank to their lowest since April, with three-month copper (HG1:COM) on the London Metal Exchang…

At the Jefferies Global Healthcare Conference in London, Pfizer CEO Albert Bourla said Chinese biotech will be…

Amphenol reported record third-quarter sales of $10.2 billion, up 65% from a year earlier, and said roughly 36…

Nvidia shares jumped in premarket trading on a strong AI outlook, while Lowe's shares fell, Investing.com repo…
