Menu
Choosing the right model for the task — power vs. cost vs. speed.
The review-first prompt is selected by default. You can switch to a direct command or download a local copy.
Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
A direct command skips the review prompt. Inspect the source before running it.
npx skills add https://github.com/fabioc-aloha/AlexAgent --skill llm-model-selection-skillThe command stays on one line. Scroll horizontally to inspect it before copying.
Prefer a local copy? Download the files currently available to SkillsMP.
Based on SOC occupation classification
Showing SKILL.md
| name | LLM Model Selection Skill |
| description | Choosing the right model for the task — power vs. cost vs. speed. |
| applyTo | **/*model*,**/*llm*,**/*copilot*,**/*claude*,**/*gpt* |
Choosing the right model for the task — power vs. cost vs. speed.
This skill depends on rapidly evolving technology. Model capabilities, pricing, and availability change frequently.
Refresh triggers:
Last validated: February 2026 (Claude 4.6 generation)
Check current state: Anthropic Models, OpenAI Models
Is Claude Opus 4.6 overkill?
Sometimes yes, sometimes no. Match the model to the task.
| Model | API ID | Best For | Input/Output (MTok) | Context | Max Output |
|---|---|---|---|---|---|
| Opus 4.6 | claude-opus-4-6 | Building agents, most intelligent | $5 / $25 | 200K (1M beta) | 128K |
| Sonnet 4.6 | claude-sonnet-4-6 | Best speed + intelligence balance | $3 / $15 | 200K (1M beta) | 64K |
| Haiku 4.5 | claude-haiku-4-5-20251001 | Near-frontier intelligence, fastest | $1 / $5 | 200K | 64K |
All Claude 4 models support:
Opus 4.6 and Sonnet 4.6 additionally support:
context-1m-2025-08-07 header — long context pricing applies beyond 200K)AWS Bedrock IDs: anthropic.claude-opus-4-6-v1, anthropic.claude-sonnet-4-6
GCP Vertex AI IDs: claude-opus-4-6, claude-sonnet-4-6
| Tier | Models | Best For | Relative Cost |
|---|---|---|---|
| Frontier | Claude Opus 4.6, GPT-5, Gemini 2.5 Ultra | Complex reasoning, architecture, novel problems | $$$$$ |
| Capable | Claude Sonnet 4.6, GPT-4.1, Gemini 2.5 Pro | Most coding tasks, refactoring, debugging | $$$ |
| Fast | Claude Haiku 4.5, GPT-4.1-mini, Gemini 2.5 Flash | Simple edits, formatting, boilerplate | $ |
| Capability | Frontier (Opus 4.6) | Capable (Sonnet 4.6) | Fast (Haiku 4.5) |
|---|---|---|---|
| Complex refactoring | Excellent | Excellent | Good |
| Context retention | 200K / 1M (beta) | 200K / 1M (beta) | 200K tokens |
| Extended thinking | Full depth | Supported | Supported |
| Adaptive thinking | Yes | Yes | No |
| Max output tokens | 128K | 64K | 64K |
| Nuanced judgment | Excellent | Good | Basic |
| Speed | Moderate | Fast | Fastest |
| Cost per session | $2-5 | $0.50-2 | $0.05-0.30 |
| Multi-step planning | Excellent | Excellent | Good |
| Error recovery | Self-corrects | Self-corrects | Needs guidance |
Opus 4.6: [████████████████████] Full cognitive architecture + deep thinking
Sonnet 4.6: [██████████████████░░] Most capabilities, excellent for coding
Haiku 4.5: [██████████████░░░░░░] Solid baseline, fast responses
With Opus 4.6, Alex can:
With Sonnet 4.6, Alex gets:
With Haiku 4.5, Alex has:
| Session Type | Recommended Model | Rationale |
|---|---|---|
| Architecture/design | Opus 4.6 | Worth the cost for complex decisions |
| Feature development | Sonnet 4.6 | Best balance of capability and cost |
| Bug fixes | Sonnet 4.6 or Haiku 4.5 | Depends on complexity |
| Documentation | Haiku 4.5 | Simple edits, fast turnaround |
| Large codebase analysis | Sonnet 4.6 (1M beta) | Extended context window up to 1M tokens |
| Model | Reliable Knowledge | Training Data |
|---|---|---|
| Opus 4.6 | May 2025 | Aug 2025 |
| Sonnet 4.6 | Aug 2025 | Jan 2026 |
| Haiku 4.5 | Feb 2025 | Jul 2025 |
When using Auto in VS Code Copilot, the model switches dynamically based on task complexity. Alex cannot detect which model is currently running.
| Task | Why Opus Required |
|---|---|
| Meditation/consolidation | Meta-cognitive protocols need full reasoning depth |
| Self-actualization | Comprehensive architecture assessment |
| Complex architecture refactoring | Multi-file changes, deep context |
| Bootstrap learning (new skills) | Skill acquisition needs maximum capability |
| Synapse validation/dream | Neural maintenance requires full architecture |
| Adaptive thinking tasks | Opus 4.6 uses dynamic reasoning depth for optimal results |
When user requests an Opus-level task while potentially on Auto/lesser model:
⚠️ Model Check: This task works best with Claude Opus 4.6. If you're using Auto model selection, please manually select Opus from the model picker for optimal results. Continue anyway?
If you notice:
→ Consider switching to a more capable model
If you're doing:
→ Save cost with a faster model
For Master Alex (source of truth, architecture evolution): → Always use Opus 4.6 — The cognitive architecture demands full capability
For Heirs (production deployment, user-facing): → Default to Sonnet 4.6 — Best balance of capability and cost → Allow Opus for complex tasks — User can request escalation
| Operation | Approximate Tokens | Opus 4.6 Cost | Sonnet 4.6 Cost |
|---|---|---|---|
| Read large file | 2,000-5,000 | $0.03-0.08 | $0.006-0.015 |
| Complex refactor | 10,000-20,000 | $0.15-0.30 | $0.03-0.06 |
| Full session | 50,000-150,000 | $0.75-2.25 | $0.15-0.45 |
| Meditation | 30,000-80,000 | $0.45-1.20 | $0.09-0.24 |
See synapses.json for connections.