Running Hermes on DeepSeek V4 Pro via Baseten Model APIs

Melvin Vivas · X post · 2026-08-20 · Open on X

Topics: LLM Fundamentals, LLMOps, Deployment & Monitoring · Level: beginner

Summary

The creator used leftover Baseten Model API credits to run his Hermes setup on DeepSeek V4 Pro 0813, and says he likes it. It shows that you can point an agent harness at any hosted model API provider.

Key points

• Baseten offers hosted Model APIs that you pay for with credits.
• Hermes can be set to use a different backing model, here DeepSeek V4 Pro 0813.
• Check your provider accounts for unused credits before paying for something new.

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
• DeepSeek V4 Pro 0813 · tool · baseten.co · paid
  DeepSeek large language model, served here through Baseten Model APIs.
  Also in: Running DeepSeek V4 Pro 0813 on Baseten with the Pi Agent (Melvin Vivas on X · notes)
• Hermes · tool · hermes-agent.nousresearch.com · free
  The AI agent the creator uses to automate making explainer videos. It is probably Nous Research's Hermes Agent, but the post does not say so.
  Also in: OpenAI DevDay recap: Dots, GPT-6.1 Sol, Codex Cloud, Agents API (Melvin Vivas on X · notes), Coworker: free open-source desktop AI coworker app (Melvin Vivas on X · notes), Agent Monitor: see traces, tokens and costs of your coding agents (Melvin Vivas on X · notes), Coworker: An Open-Source Desktop Agent App for Local and Cloud Models (Melvin Vivas on X · notes) and 13 more