Volodymyr Kuleshov 🇺🇦
@volokuleshov
🚀 Mercury 2.5 is here — the next generation of Mercury diffusion models.
Big gains on agentic workloads, still running at >1000 tok/sec in production.
Live today on OpenRouter — check it out 👇
Big gains on agentic workloads, still running at >1000 tok/sec in production.
Live today on OpenRouter — check it out 👇
OpenRouter@OpenRouter · Sep 11/ The fastest reasoning LLM is now live exclusively on OpenRouter.
Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON.
Built for latency-sensitive workloads.
Mercury 2.5 Preview from @_inception_ai reaches 1,107 tokens/sec through parallel token generation, with tunable reasoning, parallel tool calls, and schema-aligned JSON.
Built for latency-sensitive workloads.
0:06 1 40