Mercury 2.5 Preview: Fastest Reasoning LLM Now Live on OpenRouter
Key Info
Inception AI's Mercury 2.5 Preview is now live exclusively on OpenRouter, claiming the title of fastest reasoning LLM with 1,107 tokens/sec via parallel token generation.
Highlights
- Reaches 1,107 tokens/sec using parallel token generation, built for latency-sensitive workloads.
- Offers tunable reasoning depth and parallel tool calls.
- Outputs schema-aligned JSON for structured use cases.
- Available now exclusively on OpenRouter.