Vercel AI Gateway
| | | | | | | | | | | | | | | | | | | \| \| \| \| \| \| | | | | | | | | | | | | | | | \| \| \| \| on:
Model details
Mercury Coder Small Beta is a specialized text-to-text model built to enhance developer productivity through rapid, responsive interactions. By utilizing a unique discrete diffusion architecture, the model achieves operational speeds five to ten times faster than many optimized alternatives. This design intent focuses on providing a seamless experience for code completion and chat-based iterations, allowing developers to maintain momentum during complex programming tasks without sacrificing performance.
Beyond its architectural speed, the model demonstrates strong ethical reasoning and grounding capabilities, as evidenced by high scores in dilemma-based evaluations. Its design supports practical, real-world application by maintaining internal logical coherence and stability in reasoning. With its ability to handle extensive context, the model is well-suited for developers who require a reliable, high-performance tool for drafting code and managing large-scale technical workflows efficiently.
Transparent token rates
Rates are shown per one million tokens. Combined means one million input plus one million output tokens.
Vercel AI Gateway
| | | | | | | | | | | | | | | | | | | \| \| \| \| \| \| | | | | | | | | | | | | | | | \| \| \| \| on: