Kimi K3 Hits OpenRouter: 2.8T Parameters, 1M Context Length
AccBalanced · x · 2026-08-01
Moonshot AI's Kimi K3 is now available on OpenRouter. The model features 2.8T parameters and supports a massive context window of 1 million tokens, with input and output pricing set at $2.90 and $14 per million tokens, respectively.
K3 focuses on multimodal reasoning, making it highly suitable for complex coding, knowledge work, and long-horizon agentic workflows. It utilizes KDA and Attention Residuals in its architecture for computational efficiency. A serverless deployment option is currently provided by waferai.
Related event: Moonshot's Open-Source Kimi K3 Lands on Multiple Platforms(4 posts)→
More from Models
- Users report Gemini's memories can't actually be deleted even after wiping chat history — ThrowRA_Purpose2025 · 2026-10-16
- OpenAI stealth-testing mysterious internal model 'Aeon' in Codex desktop app and Dots — cedric_chee · 2026-10-16
- Argon edges out astra as daily driver, but Claude still wins heavy coding work — iruletheworldmo · 2026-10-16
- NVIDIA ships FP4-quantized Qwen3.8-Flash for local use, trending on Hugging Face — nvidia · 2026-10-16
- RoboVista benchmark: Gemini-4 Argon hits 81.9% on robotics understanding — berkeley_ai · 2026-10-16
- Dev reports decision model jev beats gpt-6-luna on quality in real training pipeline — genmon · 2026-10-16