Add corrections, implementation notes, pricing changes, or usage caveats for other readers.
Input modalities
Output modalities
Capabilities
262,144 tokens
Recent tweets and retweets from NovitaAI
KV cache is becoming increasingly important for production-scale inference and agent workloads.
Excited to contribute PegaFlow to the @vllm_project ecosystem — a production-grade external KV cache system for vLLM ⚡
• KV survives restarts and model switches
• Shared cache…
DeepSeek V4 Flash is still free on Hermes @NousResearch via Nous Portal — powered by Novita AI.
Available on Hermes as a model provider ⚡
If you’re building agents, autonomous workflows, tool-use systems, or experimenting with long-horizon reasoning, now’s a great time to…
🚀 Ring-2.6-1T is now open source (from @AntLingAGI).
Now 90% off on @OpenRouter via @novita_labs — a great time to start building and experimenting with large-scale agent workflows.
A trillion-scale reasoning model built for real-world agents.
Designed not just to answer…
Discuss this model
Add corrections, implementation notes, pricing changes, or usage caveats for other readers.