Running GLM 5.3 Flash on Baseten with the Pi Coding Agent
Melvin Vivas · X post · 2026-08-28 · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity · Level: intermediate
Summary
The creator runs the GLM 5.3 Flash model through Baseten's inference platform and uses it inside the Pi coding agent. He says it generates output faster than he can read it.
Key points
- GLM 5.3 Flash is served on Baseten with very high generation speed.
- He pairs it with the Pi coding agent for coding work.
- Fast hosted open models can power agentic coding tools.
Resources mentioned
- GLM 5.3 Flash · tool · huggingface.co · free
Low-cost model (about $0.15 in / $0.50 out per million tokens) that Theo says beats GPT-5 at agentic work.
Also in: Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), GLM-Legal: Z.ai's Legal-Domain Model Built on GLM-5.3-Flash (Melvin Vivas on X · notes), Coworker Desktop App Works with Any OpenAI-Compatible Endpoint (Melvin Vivas on X · notes) - Baseten · tool · x.com · paid
Model inference platform offering dedicated GPU deployments for serving open models.
Also in: Serving Qwen3.8 27B FP8 on an H100 with Baseten dedicated inference (Melvin Vivas on X · notes), Coworker Desktop App Works with Any OpenAI-Compatible Endpoint (Melvin Vivas on X · notes), GLM 5.3 Flash Now Available on Baseten (Melvin Vivas on X · notes), GLM-5.2 Vision on Baseten: Turning Images into Code (Melvin Vivas on X · notes) and 6 more - Pi · tool · x.com · free
A customizable coding agent that can be extended through its Extensions API and connected to several model providers.
Also in: 100-Iteration Autonomous Coding Loop with Local Qwen on an RTX 3090 (Melvin Vivas on X · notes), Pi Agent: A Highly Customizable Agent with Durable Sessions (Melvin Vivas on X · notes), Prompting an Autonomous Agent Loop: Be Specific, Show Visible Progress (Melvin Vivas on X · notes), Running an Overnight 100-Iteration Agent Loop with a Local Qwen Model (Melvin Vivas on X · notes) and 54 more
More in LLMOps, Deployment & Monitoring
- Running Qwen3.8 27B Locally on an RTX 3090 with llama.cpp and the Pi Harness
- Low-Cost Agent Run: DeepSeek V4 Flash via OpenRouter in ohmypi
- Serving Qwen3.8 27B FP8 on an H100 with Baseten dedicated inference
- AIBackends v0.7.0: Prompt Routing with Liquid AI's LFM2.5 Encoder
- GLM 5.3 Flash Now Available on Baseten
- Zero-Shot Prompt Routing with Liquid AI's LFM 2.5-Encoder-350M