Inception ships Mercury 2.5: most capable diffusion LLM at 1,107 tokens/sec, 260K context
StefanoErmon · x · 2026-09-09
Inception Labs has released Mercury 2.5, which CEO Stefano Ermon calls the most capable diffusion LLM on the market and the largest diffusion language model ever trained.
- Quality: 40% intelligence jump over Mercury 2; comparable to cost-optimized frontier models like GPT-5.6 Luna (Low), Gemini 3.5 Flash-Lite, and Claude Haiku 4.5
- Speed: 1,107 tokens/sec on widely available NVIDIA GPUs
- Context: 260K tokens
- Price: $0.20/M input, $0.75/M output, 80% off at launch ($0.04/$0.15)
- Capabilities: tunable reasoning, parallel tool calls, schema-aligned JSON
Usage has grown over an order of magnitude since Mercury 2 launched, with dozens of enterprises in production across search, voice, and coding. NVIDIA endorsed the release. Inception also shared OpenCall running live patient-call voice agents on Mercury, cutting p99 latency to one second.
More from Infra
- Analyst: Ant has the most fungible AI workload of any model provider today — BenBajarin · 2026-10-26
- Anthropic S-1: training infra edge cut per-task cost 40% and doubled revenue growth — BenBajarin · 2026-10-26
- Rewriting scaling law study: optimal synthetic data share rises from 10% to 32% with compute — heghbalz · 2026-10-26
- US states halt new data centers as 72% of Americans oppose local builds — YvesMulkers · 2026-10-26
- $5M Seed Round Can't Afford One DeepSeek Training Run: GPU-less AI Startup's Three Paths — FinanceYF5 · 2026-10-26
- HBM demand shifts: low-stack inference plans shelved, Rubin to go 12-high only — BenBajarin · 2026-10-26