Novita AI

@novita_labs

AI & Agent Cloud for Developers ⚡Join our community: discord.com/invite/YyPRAzw…

San Francisco

novita.ai

Joined September 2023

Replies Reposts Media Articles

Pinned
Novita AI
@novita_labs
Aug 27
🚀 Ling-3.0-flash-Fin from @AntLingAGI is now live on Novita AI! Launching as a Day-0 partner ⚡ 🎁 Free for 30 days. A finance-enhanced version of Ling-3.0-flash, developed with financial institutions and domain experts. 🔹 124B total parameters · 5.1B active parameters 🔹
00:00
9
Novita AI
@novita_labs
47m
The future of AI is open—and open models need infrastructure that makes them practical to build with. Proud to support the @huggingface ecosystem by giving developers accessible, cost-efficient inference for open models like GLM-5.3 and GLM-5.3-Flash.
Jensen Huang
@JensenHuang
3h
Exciting day for NVIDIA and @huggingface. Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty. They allow every developer, startup, university, industry and country to build with, customize and benefit from AI. Thank you
3
Novita AI
@novita_labs
22h
97.1% cache hit rate—the highest among GLM-5.3 providers in this OpenRouter snapshot. More repeated context served from cache, with an observed effective input cost of $0.2933/M tokens via Novita AI. Built for efficient agent workloads.
3
Novita AI
@novita_labs
Sep 1
Which one feels closest to the real thing? If you had to choose one model to build with, which one would you pick? One prompt. Four frontier models. One Temple Run-inspired 3D endless runner. GLM-5.3 — 4,689 tokens, $0.019462 GLM-5.3-Flash — 3,360 tokens, $0.000731 Kimi K3 —
00:00
7
Novita AI
@novita_labs
Aug 29
One prompt. Four frontier models. One Contra-style auto-playing game. GLM-5.3 — 3,483 tokens, $0.013786 GLM-5.3-Flash — 3,947 tokens, $0.000897 Kimi K3 — 3,345 tokens, $0.043599 Qwen3.8-Flash — 10,363 tokens, $0.004687 The interesting question is not only which model performs
00:00
7