Introducing Anannas AI One API for 500+ models with sub‑ms overhead latency and real observability; route, monitor, scale. Read our blog: https://t.co/D2B039IAAT

Check out how good the new Kimi-K2 thinking is for biology tasks on https://t.co/hU2o9fTwUh. In our testing it has been a very strong model.

Kimi K2 Thinking is LIVE on Anannas! > Open Sourced Reasoning MoE model > 1T total, 32B active parameters, 256K context length > Interleaved thinking in agentic tool-use, strong benchmark scores and vibe tests. Try now: https://t.co/2kBXs67laM

bruh no way kimi researchers using @anannas_ai wow

on a side note, uc berkeley researchers from bair lab are using @anannas_ai

⚡️Today marks a big milestone for Nebius. We’re launching Nebius Token Factory, the evolution of Nebius AI Studio, built to make open-source AI production-grade. Token Factory transforms raw open models into governed, scalable systems with dedicated inference, sub-second

Coming soon 🍍

Minimax M2 is LIVE on Anannas! - Agent & Code Native, at 8% Claude Sonnet Price, ~2x faster - Global FREE model (for a limited time) Try now: https://t.co/N7gcVXfGlL

@OpenBioAI uses @anannas_ai too!!

milestone update.

NousCon last night was a massive success! Thank you to everyone who showed out for our biggest event of the year. The future of open source AI is incredibly bright. S/o @rosstaylor90 and @dhruv31415 for coming to speak, @poetengineer__ and @johnkarborn for their epic live art

Anannas x @NousResearch Anannas is proud to support Nouscon where open science and research meets the frontier. 📍San Francisco | 24 October 2025

https://t.co/zdwjjpJLQs

Anannas x Langfuse ⚡️ - Get dual layer observability - Anannas tracks gateway metrics - Langfuse captures your application traces and debugging flow - Full visibility from model selection to production executions Integration guide 👇

this @anannas_ai merch is too classy frr and btw we are close to 2k users!✨

over 2B+ of tokens processed within few weeks (doubled in 4 days) since we started rolling out @anannas_ai with most requests on diwali eve. thank you for your attention to this matter.

claude haiku 4.5 - now at 30% off. live now at https://t.co/YIqlcpMULe go and melt those gpus!

@sciraai inference via @anannas_ai ofc

Claude Haiku 4.5 is LIVE on Anannas! Haiku 4.5 matches the coding performance of Sonnet 4 at 1/3rd cost and >2x speed. Try now: https://t.co/xpEcD7nuKL

Introducing Playground! Test any model with detailed metrics in seconds. Free credits included. Try now: https://t.co/5HBr0HrIS9