Most AI has an off switch. It looks like a building: one datacenter, one provider, one cloud account that can be closed, one government that can say no. If the thing you depend on lives in one place, someone else decides whether it stays on. Parallax is our attempt to train models that don’t have that switch.

14 open models, one endpoint, every one of them running inside a hardware-attested TEE. That's the Chutes catalog today: Kimi K3 and GLM-5.2 with 1M context, DeepSeek V4 Flash, Qwen3.8-27B, Gemma 4 31B, and Nemotron-3-Nano from $0.0245 per million input tokens. The list changes often. Any OpenAI-compatible client works. Set the base URL to llm.chutes.ai/v1 and keep the rest of your code.