Mercury 3 launches: 1,068 tok/s, 1M context, 50% off at $0.10/$0.35 per million tokens
StefanoErmon · x · 2026-10-20
Inception Labs officially launches diffusion LLM Mercury 3:
- Quality: on par or better than speed-optimized frontier models like GPT-6 Luna and Claude Haiku 5.5
- Speed: 1,068 tokens/sec on NVIDIA GPUs, 4-8x faster than peers
- Context: 1M tokens, up from 260K in Mercury 2.5
- Price: $0.20/$0.70 per million in/out, launch discount at $0.10/$0.35, cached tokens 90% off input price
- Scaling: 40x+ larger than Mercury 1 with 3x benchmark gains, arguing diffusion grows intelligence without proportional latency
In TinyFish's production web-agent harness on 50 live Mind2Web tasks, Mercury 3 completed 50%, beating GPT-6.1-Sol at the same token volume and agent steps for a fraction of the cost. Available via Inception API, OpenRouter, Baseten and Vercel; early adopters use it for voice support, tutoring, data engineering and web navigation.
More from Models
- Deutsche Bank: Meta's Muse still leads ChatGPT in downloads and DAUs 36 days post-launch — alexandr_wang · 2026-10-20
- Uncensored DeepSeek V4.1 Flash FP8 finetune trends on Hugging Face — dealignai · 2026-10-20
- ChatGPT caught silently swapping GPT-5.6 High for GPT-6 at medium thinking — DepositameAMiBCP · 2026-10-20
- MiniMax M3.1 Flash goes live in Command Code with 1M context, free for now — MiniMax_AI · 2026-10-20
- User slams Xiaomi MiMo over hard-to-cancel $60 subscription — bookwormengr · 2026-10-20
- Strata 2 beta runs at half speed? Dual-4090 user reports 155→95 tok/s — Lost-Vermicelli-6252 · 2026-10-20