Running a Personal AI Agent for $0.69/Day with DeepSeek V4 Flash
Melvin Vivas · X post · 2026-07-08 · Open on X
Topics: LLMOps, Deployment & Monitoring, AI Agents, Tool Use & MCP · Level: intermediate
Summary
A real cost figure: one day of running DeepSeek V4 Flash through OpenRouter as the main agent model in Hermes cost $0.692. It was used for personal-assistant tasks, not coding. Cheap, fast models can make an always-on personal agent very affordable.
Key points
- One day of use cost $0.692.
- Model: DeepSeek V4 Flash, accessed through OpenRouter.
- Used as the main agent model in Hermes for personal-AI tasks, not coding.
- Routing a cheap 'flash' model through a gateway like OpenRouter keeps daily agent costs low.
Resources mentioned
- OpenRouter · tool · openrouter.ai · free
A single OpenAI-compatible API that routes requests to hundreds of models from many providers, with one bill and model fallbacks.
Also in: Stealth Model 'Space Bunny' Revealed as MiniMax M3.1 Flash (Melvin Vivas on X · notes), NVIDIA Nemotron 3.5 Super VL now on OpenRouter (Melvin Vivas on X · notes), OpenRouter serves image models, including FLUX 3 Image Klein (Melvin Vivas on X · notes), Comparing Opus 5.5, GPT-6 Astra and Grok 4.7 on OpenRouter (Melvin Vivas on X · notes) and 53 more - DeepSeek V4 Flash · tool · huggingface.co · free
Cheap DeepSeek model whose intelligence-index score is roughly equal to GPT-5's.
Also in: Is AI Getting Cheaper? How to Measure LLM Cost Per Task and Per Intelligence Level (Melvin Vivas on X · notes), Low-Cost Agent Run: DeepSeek V4 Flash via OpenRouter in ohmypi (Melvin Vivas on X · notes), Running Codex with DeepSeek V4 Flash through OpenRouter (Melvin Vivas on X · notes), LFM2.5-2.6B Matches DeepSeek-V4-Flash on Tool Calling; LEAP Fine-Tuning (Melvin Vivas on X · notes) and 4 more - 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: Why Simpler Agent Bots Appeal to Non-Technical Users (Melvin Vivas on X · notes), Using Grok Bot to orchestrate Claude Code, Codex and Hermes (Melvin Vivas on X · notes), Coworker: A Desktop AI Assistant App, Not a Coding Agent (Melvin Vivas on X · notes), Grok Bot's Real Competitors: OpenClaw and Hermes (Melvin Vivas on X · notes) and 18 more
Try this
- Set up a personal AI assistant agent that runs on a cheap model through OpenRouter, and track its daily cost.
More in LLMOps, Deployment & Monitoring
- aibackends 0.3.0: Model Caching Speeds Up PII and OCR Inference
- Monitor GPU Usage With nvtop Instead of nvidia-smi
- Cost-Saving Model Fallback Chain: Grok → Codex → OpenRouter DeepSeek
- Hosting a Personal AI Agent: Local Mac Mini vs Cloud VM Privacy Trade-off
- Frontier Model Costs: Why Top Models Can Sink a Solo Dev's MRR
- GLM 5.2 Hits 446 tok/s on Fireworks AI