Mercury Decide adds image input on OpenRouter
- Source
- x.com
- Date
Mercury Decide from @_inception_ai now accepts image input on OpenRouter Put images alongside text in the state of a Decisions request, and Mercury Decide answers your typed questions from what's in the image: a choice, a score, or a yes/no with a probability attached Pricing is unchanged: free endpoint, or $0.02/M input with zero data retention. Images bill as input tokens https://t.co/5sumvRshSm
Context
Mercury Decide can now use an image as evidence for a structured decision on OpenRouter. The caller supplies images alongside text and asks for a defined answer type, such as a choice, score or yes/no response with a probability. The announcement extends that decision interface to visual input.
The model documentation describes probabilities returned directly from the model and suggests escalating uncertain cases to a person. This makes the output usable in a decision workflow without first interpreting a prose answer. Images count toward input billing, according to the launch post.
- token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
Checking sign-in…
Loading comments…