Diffusion language models have carried one question since birth: can the speed advantage of parallel generation survive scaling? For over a year, autoregressive models grew stronger by stacking parameters, while diffusion LLMs stayed in the "small but fast" proof stage. Inception answered yesterday with its third-generation model Mercury 3, which the company calls the most capable diffusion LLM released to date (official blog: https://www.inceptionlabs.ai/blog/introducing-mercury-3).
40x Scale, Speed Intact
Mercury 3's core narrative is that text diffusion scales. Per the official announcement, its total parameter count is more than 40x that of Mercury 1 (launched June 2025), intelligence on standard benchmarks has risen roughly 3x from Mercury 1 mini, yet inference speed stays above 1,000 tokens per second — 1,068 tokens/sec on NVIDIA GPUs. The context window jumps from 260K tokens (Mercury 2.5) straight to 1 million.
On pricing: 0.20 USD per million input tokens and 0.70 USD per million output tokens, halved to 0.10/0.35 USD during launch, with cached tokens billed at 90% off the input price.
Vendor Benchmarks and Production Data
Vendor benchmarks claim Mercury 3 outperforms GPT-6 Luna and Claude Haiku 5.5 on tests including GPQA Diamond, IFBench, and SWE-Bench Atlas while running 4-8x faster. The production evidence is more concrete: on 50 live Mind2Web navigation tasks, Mercury 3 completed 50%, which the company says is significantly more than GPT-6.1-Sol, using the same token volume and agent steps at a fraction of the per-token cost. Smart-glasses search startup Octen AI reported a median generation time of 0.9 seconds and end-to-end response of 2.2 seconds.
Note: all scores above are vendor-reported and not yet independently reproduced.
The Gap Between Claim and Measurement
Third-party review site explainx ran a cross-check the same day: a single OpenRouter provider showed a measured median of about 254 tokens/sec with 1.91s P50 latency — more than 4x below the official 1,068 figure. Two other details the company left out: the exact parameter count is undisclosed, and the weights are closed — API-only delivery (Inception API, OpenRouter, Baseten, Vercel, with an OpenAI-compatible interface and 100 million free tokens for new accounts).
Why It Matters
If scaling laws hold for diffusion — which is exactly Inception's central claim — the industry gains a second scaling path independent of autoregression: intelligence can grow without inference getting slower. For browser agents, voice, and real-time search, where every step waits on the model, that is a structural win; Inception also launched Mercury Voice (first answer token under 170ms) and Mercury Decide (benchmarking against Jev) in the same wave, a portfolio clearly betting on real-time AI.
But the 254-vs-1,068 gap is a reminder: the "1,000+ tokens per second" in a vendor's announcement and the number coming out of your own gateway may not be the same. Next time a model launches, ask "what does it measure in practice?" before putting an architecture migration on the roadmap.