# Model Cost Compare

Trigger when the user asks which model to use, wants to compare model costs, says...

- Repository: https://github.com/mergisi/awesome-openclaw-agents (4042 stars)
- Category: Engineering
- License: MIT
- Last updated: 2026-10-28
- Runs scripts: no, instructions only

## Install

Claude Code: `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -g -a claude-code -y`
Codex: `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -g -a codex -y`
Cursor: `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -g -a cursor -y`
Gemini CLI: `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -g -a gemini-cli -y`

## Description

Trigger when the user asks which model to use, wants to compare model costs, says "what's cheapest for this task", "should I use Opus or Sonnet", "can a smaller model handle this", or "/model-cost-compare". Estimates token cost across Opus 4.6, Sonnet 4.6, GLM-5.1, Minimax M2.7, and local Gemma 4, then recommends the cheapest model capable of the task.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# Model Cost Compare

Given a task description (and optionally a rough prompt / input size), estimate the cost of running it on each available model tier and recommend the cheapest one that can actually do the job.

## When to use

- "Which model should I use for X?"
- "Is it worth running this on Opus or will Sonnet do?"
- "Can I offload this to a local model?"
- "/model-cost-compare, classify 10k support tickets"

## Pricing table (indicative, always flag as "check provider docs")

Use these rough figures. They are **not** exact; confirm before quoting real numbers to the user.

| Model | Tier | Input ($/1M tok) | Output ($/1M tok) | Context | Strengths |
|---|---|---|---|---|---|
| Opus 4.6 (1M) | Frontier | ~$15 | ~$75 | 1M | Agentic, long-context, hard reasoning |
| Sonnet 4.6 | Mid | ~$3 | ~$15 | 400k | Everyday coding, agents, drafting |
| GLM-5.1 | Budget hosted | ~$0.60 | ~$2.20 | 256k | Cheap bulk work, decent reasoning |
| Minimax M2.7 | Budget hosted | ~$0.40 | ~$1.80 | 256k | Very cheap, OK for templated output |
| Gemma 4 (local) | On device | $0 marginal | $0 marginal | 32k | Free but slow, weak at multi-step logic |

> Indicative pricing as of OpenClaw 2026.4.11. Check the provider docs before billing decisions.

## Instructions

The rest: https://github.com/mergisi/awesome-openclaw-agents/blob/HEAD/skills/claude/model-cost-compare/SKILL.md