model-selection

Compare LLM deployment paths and models across cost, latency, privacy, and capability.

Updated Apr 3, 2026

Search Tags:#deployment #llm #evaluation #fine-tuning #prompt-engineering #model-selection #api-vs-local

Ready to run

npx skills add https://github.com/Victoriakaey/build-reliable-agents --skill model-selection-victoriakaey

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: model-selection
Source: https://github.com/Victoriakaey/build-reliable-agents/tree/main/skills/model-selection
Command: npx skills add https://github.com/Victoriakaey/build-reliable-agents --skill model-selection-victoriakaey

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

The Skill helps teams select the optimal deployment path and model for an LLM application by balancing cost, latency, privacy, and capability.

Core Features & Use Cases

API vs Local decision guidance for choosing between hosted models or on-device inference.
Provider/model tier comparisons and structured decision workflows from prototyping to production.
Guidance on recording configurations, evaluations, and prompt-engineering considerations to support reproducible deployments.

Quick Start

Outline your constraints, compare deployment options, and record the final decision in your project log.

Frequently Asked Questions about model-selection

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I choose between API and local deployment for my LLM application?▼

To choose between API and local deployment, you must weigh cost, latency, privacy, and capability constraints. Structured decision workflows help compare hosted models against on-device inference based on your specific data sensitivity and hardware environment.

What is the best way to compare LLM provider and model tiers for production?▼

The best way to compare LLM provider and model tiers is using a structured decision workflow that evaluates capability against cost and latency. Capturing constraints and tradeoffs in a structured log ensures reproducible deployments from prototyping to production.

How do I balance cost and latency when selecting an LLM deployment path?▼

You balance cost and latency by capturing hardware constraints, deployment environment, and data sensitivity as explicit inputs. This allows teams to systematically evaluate deployment paths and record the resulting tradeoffs for reproducible configuration.

When do I need to record LLM configuration and prompt engineering tradeoffs?▼

You need to record LLM configuration and prompt engineering tradeoffs throughout prototyping to production to support reproducible deployments. Keeping a structured decision log of artifacts and evaluations maintains consistency across different model tiers and deployment paths.

Does data sensitivity affect whether I should use API or local LLM inference?▼

Data sensitivity directly impacts API versus local LLM inference decisions by acting as an explicit input constraint. High privacy requirements often favor local deployment, while balancing this against available hardware and required model capability dictates the final path.

Can I use this for evaluating fine-tuning versus prompt engineering for my model?▼

You can use this to guide prompt engineering considerations alongside deployment path and model selection. It helps weigh configuration tradeoffs and capture evaluations, ensuring your team records the optimal approach between fine-tuning and prompt adjustments in a decision log.