Running DeepSeek V4 Pro on Baseten with the Pi Agent Harness
Melvin Vivas · X video post · 2026-08-20 · Open on X
Topics: AI Agents, Tool Use & MCP, LLMOps, Deployment & Monitoring, AI Dev Tools & Productivity · Level: intermediate
Summary
Melvin shows DeepSeek V4 Pro (0813) served on Baseten and used inside the Pi coding-agent harness. He points out how fast it is. The post shows that you can pair an open model hosted by an inference provider with any agent harness.
Key points
- Model: DeepSeek V4 Pro, 0813 release.
- Hosted on Baseten.
- Run through the Pi (@pidotdev) agent harness.
- The creator was struck by DeepSeek's speed on this setup.
- You can mix and match the model, the host and the agent harness.
Resources mentioned
- 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), Running GLM 5.3 Flash on Baseten with the Pi Coding Agent (Melvin Vivas on X · notes), GLM 5.3 Flash Now Available on Baseten (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 - DeepSeek · tool · deepseek.com · free
DeepSeek's updated Flash model, said to be faster with shorter outputs, available through DeepSeek's web app and API.
Also in: DeepSeek-V4.1-Flash-1017 release: better benchmarks, shorter outputs (Melvin Vivas on X · notes), Open models now dominate token volume on Vercel AI Gateway (Melvin Vivas on X · notes), jina-ocr-v1: Turning PDFs, Scans and Tables into Markdown (Melvin Vivas on X · notes), Bolt.new Adds Open Models (GLM, DeepSeek, Kimi) via Bolt Forge (Melvin Vivas on X · notes) and 5 more
Try this
- Connect a model hosted on Baseten to the Pi harness and compare speeds.
More in AI Agents, Tool Use & MCP
- Running a Local Ornith Model as the Backend for a Hermes Agent
- Mixture-of-Agents Setting Was Quietly Using Up Codex/ChatGPT Quota
- Mind Viruses: How Bad Ideas Spread Through Multi-Agent LLM Systems
- Free Colab Notebooks: LFM2.5 2.6B Tool Calling and Benchmarks
- DeepSeek harness: open-source agent with an inspectable trajectory view
- Agent Loops in ML Engineering: Liquid AI's Vibe-Coded Tokenizer Trainer