Model Routing

Picks the Claude model tier (Haiku, Sonnet, Opus, Fable) and effort level for a task class, with current model IDs and per-token prices. Use when the user asks which Claude model to run, wants to cut API or agent spend by routing work to cheaper tiers, needs exact model IDs or prices for a routing table, or is setting the model on a subagent or Task call. Do not use for ordinary coding, ORM or database "models", ML model training, or general cost questions that do not involve choosing a Claude model.

48 stars 6 forksAI, LLMs & Agents Plugin marketplace

Install

Claude Code plugin
/plugin marketplace add frankxai/claude-skills-library

The repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add frankxai/claude-skills-library --skill model-routing
Manual install
git clone --depth 1 https://github.com/frankxai/claude-skills-library.git /tmp/claude-skills-library
mkdir -p ~/.claude/skills
cp -r /tmp/claude-skills-library/packs/skills-with-evals/skills/model-routing ~/.claude/skills/model-routing

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# Model Routing

Choose the cheapest Claude tier that finishes the task, set its effort level, and escalate only on a
measured failure. Apply this when a model is being chosen. Do not run a routing analysis before every
task.

## Current models

Prices checked 2026-11-11 against the model pricing table at
https://platform.claude.com/docs/en/about-claude/pricing; model IDs against the claude-api skill's
model table (cached 2026-11-03). Prices are first-party API rates in USD per million tokens. Before writing these into code, re-check them with
`GET /v1/models` (or `client.models.list()`) and the models overview at
https://platform.claude.com/docs/en/about-claude/models/overview. Model IDs are complete as written: never
append a date suffix.

| Tier | Model ID | Input USD/1M | Output USD/1M | Context |
|---|---|---|---|---|
| Haiku | `claude-haiku-5-5` | 0.10 (0.50 when the prompt is over 100,000 tokens) | 0.50 (2.50 when the prompt is over 100,000 tokens) | 1M |
| Sonnet | `claude-sonnet-5-5` | 2.00 | 10.00 | 1M |
| Opus (default) | `claude-opus-5-5` | 4.00 | 20.00 | 1M |
| Fable (escalation only) | `claude-fable-5-2` | 8.00 | 40.00 | 1M |

Haiku's prompt length counts every input token, cache reads and writes included, and each request
is priced on its own. `routing-rules.json` in this folder carries the same IDs and prices in
machine-readable form, including the Haiku over-100K rates. Its
Read the full skill on GitHub

Details

Skill name
model-routing
Path
packs/skills-with-evals/skills/model-routing/SKILL.md
License
MIT
Repo updated
18 November 2026

FAQ

What does the Model Routing skill do?

Picks the Claude model tier (Haiku, Sonnet, Opus, Fable) and effort level for a task class, with current model IDs and per-token prices. Use when the user asks which Claude model to run, wants to cut API or agent spend by routing work to cheaper tiers, needs exact model IDs or prices for a routing table, or is setting the model on a subagent or Task call. Do not use for ordinary coding, ORM or database "models", ML model training, or general cost questions that do not involve choosing a Claude model.

How do I install the Model Routing skill?

Claude Code plugin: /plugin marketplace add frankxai/claude-skills-library. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Model Routing popular?

It lives in frankxai/claude-skills-library, which has 48 GitHub stars and 6 forks.

Related skills

Acos Meta

48

frankxai/claude-skills-library

ACOS self-description and configuration skill. Documents how ACOS works, how to extend it, how to add new skills/commands/agents, and how to debug the hook system. Use when building new ACOS capabilities, understanding the system architecture, or onboarding to ACOS for the first time.

Software Development

Acos Visual Gen

48

frankxai/claude-skills-library

Generate research-grounded visuals using the InfoGenius pipeline. Use when creating infographics, diagrams, educational visuals, or any image that benefits from factual accuracy. Supports 8 visual styles (3D, technical, minimalist, photorealistic, futuristic, vintage, cartoon, standard) and 4 audience levels.

Images, Video & Audio

Agent Harness Construction

48

frankxai/claude-skills-library

Shape an agent's tools, observations, and recovery without adding a second coordinator. Use when defining a tool, a skill, a hook, or a worktree lane.

AI, LLMs & Agents

Neutron

48

frankxai/claude-skills-library

Spend fewer tokens without lowering the ceiling. Use when a task will take more than about ten tool calls, before spawning subagents or choosing a model for delegated work, when context is filling up, or on "save tokens", "token budget", "cheaper way", "which model", "optimise this prompt", "this is burning context". Tightens a multi-part ask, picks model tier, reasoning effort, execution shape and output profile, and states the choice in one line.

AI, LLMs & Agents

Model Routing

48

frankxai/claude-skills-library

Intelligent model selection — routes tasks to Haiku (fast/cheap), Sonnet (balanced), or Opus (complex/strategic) by analyzing task complexity. Use when deciding which model to run, optimizing cost vs quality, or building a tiered routing layer.

AI, LLMs & Agents

Openai Agentkit

48

frankxai/claude-skills-library

Build production multi-agent systems with OpenAI AgentKit and the Agents SDK — orchestration, handoffs, and routines. Use when writing agents against OpenAI's AgentKit/Agents SDK or porting an agent design to the OpenAI stack.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.