Will the OpenRouter LLM input:output token ratio exceed 100 in June 2026?
2
100Ṁ512026
30%
chance
1H
6H
1D
1W
1M
ALL
This will resolve by taking the most popular model by $ volume (i.e. token volume * input token price) on OpenRouter, and considering a 7 day unweighted average of “prompt tokens divided by (output tokens + reasoning tokens)”
For example, currently, the top model by the above criteria is Sonnet 4, https://openrouter.ai/anthropic/claude-sonnet-4/activity, and the average would be about 50.
This will resolve using data from Jun 1-7 2026.
This question is managed and resolved by Manifold.
Get 
1,000 to start trading!
1,000People are also trading
Related questions
Will total processed tokens by Open Router LLMs exceed 10 trillion in any single week by the end of 2025
47% chance
In December 2025, a model by which company will be the most used on OpenRouter LLM Rankings?
Will a flagship (>60T training bytes) open-weights LLM from Meta which doesn't use a tokenizer be released in 2025?
20% chance
MMLU 99% #3: Will SOTA for MMLU (average) pass 99% by the start of 2026?
6% chance
What will be true of OpenAI's best LLM by EOY 2025?
Conditional on OpenAI releasing an open-source LLM in 2025, will it exceed o3-mini in AIME 2025 score?
65% chance
Which lab will publish the model leading OpenRouter monthly rankings EOY 2025?
When will a non-Transformer model become the top open source LLM?
Which High-risk threshold as defined by OpenAI will be reached first by an LLM, whether or not that LLM is released?
MMLU 99% #5: Will SOTA for MMLU (average) pass 99% by the start of 2028?
44% chance