For the past two years, nearly every production LLM has generated text the same way: autoregressively, one token at a time. That ties cost and latency directly to reasoning depth — the more a model thinks, the slower and pricier the answer. Inception took a different route: diffusion language models (dLLMs) draft a whole span of tokens, then refine it in parallel. On September 8 the company released Mercury 2.5, calling it its most capable production diffusion model yet.
The specs: +40% intelligence at 1,107 tokens/sec
The numbers are dense: a 40% intelligence jump over Mercury 2, positioned against cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5; 1,107 tokens per second on widely available NVIDIA GPUs; a context window extended to 260K tokens (the press release confirms the previous generation sat at 128K); and pricing of $0.20 per million input tokens / $0.75 output, slashed to $0.04/$0.15 at launch. Capability-wise it adds tunable reasoning, parallel tool calls, and schema-aligned JSON output. The company also calls it "to our knowledge, the largest diffusion language model ever trained" — a vendor claim, not a third-party verdict.
Production numbers before benchmarks
Inception's methodology deserves note: the company says this release's evals were sharpened with customer feedback and production failure cases, not benchmarks alone. Two deployment numbers stand out. OpenCall, which builds AI phone agents, reports P99 response time falling from several minutes to one second and P50 from 0.4s to under 0.2s after switching. Augment Code moved context compaction to Mercury and cut latency 82% (roughly 150 seconds down to 27) while reducing cost 90% with quality maintained. Previews of Mercury Voice (sub-170ms time-to-first-token) and Mercury Router (a dLLM that routes prompts across models) opened alongside.
The sober part: no independent benchmarks yet
Italian outlet tech-insider.org cautions that days after launch, no independently published benchmark existed for Mercury 2.5 — the 1,107 tokens/sec figure is measured on Inception's own infrastructure, and the right move is testing latency on your own workload. On X, observers did the arithmetic against Artificial Analysis' September 8 speed leaderboard (about 221 t/s at the top): if the number holds, it is roughly five times the leader — and "if it holds" is doing a lot of work in that sentence.
So what: if your agents are full of high-frequency short calls — query rewrites, reranking, compaction, routing — dLLMs have moved from papers into a permanent column of the model-selection spreadsheet. But until you benchmark it yourself, keep the word "fastest" in quotes.