New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Model Cost Compare

by mergisi in mergisi/awesome-openclaw-agents

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…

MITAuto-check passedAI & LLM Engineering

Install Model Cost Compare

skills CLI
$ npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mergisi/awesome-openclaw-agents model-cost-compare --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mergisi/awesome-openclaw-agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/claude/model-cost-compare .claude/skills/model-cost-compare && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
model-cost-compare
GitHub stars
4k
Token cost
~1k tokens
SKILL.md length
412 words
Files
1
Skills in repo
16
Repo updated
First seen
Licence
MIT

At a glance

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…

  • Works in 5 steps: Parse the user's task. Extract → Rule out incapable models. Use this… → For each surviving model, compute → …
  • The user asks which model to use
  • SKILL.md covers When to use, Pricing table (indicative —…, Instructions and Output example, plus 2 more sections
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Model Cost Compare is an agent skill from mergisi/awesome-openclaw-agents. 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.

Its SKILL.md is about 1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in AI & LLM Engineering, covering LLM cost and token optimization. It works with MiniMax and Zhipu GLM. The repository describes itself as: 162 production-ready AI agent templates for OpenClaw. SOUL.md configs across 19 categories. Submit yours! The licence is MIT.

When your agent uses it

  • The user asks which model to use
  • Wants to compare model costs
  • Says whats cheapest for this task
  • Should I use Opus

Example prompts

  • “s cheapest for this task”
  • “should I use Opus or Sonnet”
  • “can a smaller model handle this”
  • “/model-cost-compare”

Workflow steps

5 steps, taken from the first numbered list in SKILL.md.

  1. Parse the user's task. Extract
  2. Rule out incapable models. Use this capability floor
  3. For each surviving model, compute
  4. Print the comparison as a Markdown table sorted cheapest first. Bold the recommended row.
  5. End with a one-line recommendation: Recommended: — <1-sentence reason>.

What it can do on your machine

Read from SKILL.md and the folder at commit 05820c5. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Model Cost Compare loads about 1k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 412 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~93
When it runs · the whole SKILL.md, loaded when a task matches
~1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mergisi/awesome-openclaw-agents at commit 05820c5, republished under its MIT licence (© mergisi). 412 words, ~1,015 tokens.

Download SKILL.mdSave it as .claude/skills/model-cost-compare/SKILL.md (or your agent's skills folder).
name
model-cost-compare
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.

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.

ModelTierInput ($/1M tok)Output ($/1M tok)ContextStrengths
Opus 4.6 (1M)Frontier~$15~$751MAgentic, long-context, hard reasoning
Sonnet 4.6Mid~$3~$15400kEveryday coding, agents, drafting
GLM-5.1Budget hosted~$0.60~$2.20256kCheap bulk work, decent reasoning
Minimax M2.7Budget hosted~$0.40~$1.80256kVery cheap, OK for templated output
Gemma 4 (local)On device$0 marginal$0 marginal32kFree but slow, weak at multi-step logic

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

Instructions

  1. Parse the user's task. Extract:
    • Task type: reasoning, extraction, classification, drafting, translation, agentic tool use, long-context synthesis.
    • Input size estimate: in tokens. If the user says "10k tickets averaging 500 tokens", that's 5M input tokens. If unknown, ask for a rough size.
    • Output size estimate: short label? full essay? JSON record?
    • Volume: one-off or batch?
  2. Rule out incapable models. Use this capability floor:
    • Agentic multi-tool flows with long reasoning → Opus or Sonnet only.
    • Structured extraction / classification with clear schema → any tier, including Gemma 4 local.
    • Long-context synthesis (>400k tokens) → Opus only.
    • Privacy-sensitive data that cannot leave the machine → Gemma 4 local only.
  3. For each surviving model, compute:
    cost = (input_tokens / 1_000_000) * input_price
     + (output_tokens / 1_000_000) * output_price
    Multiply by volume. Show your arithmetic so the user can sanity-check.
  4. Print the comparison as a Markdown table sorted cheapest first. Bold the recommended row.
  5. End with a one-line recommendation: Recommended: <model> — <1-sentence reason>.
Show full SKILL.md (85 more words)Show less

Output example

Input: "Classify 10,000 customer support emails into 5 categories. Avg 400 input tokens, 20 output tokens."

Total tokens: 4M input, 200k output

| Model       | Input cost | Output cost | Total   | Capable? |
|-------------|-----------:|------------:|--------:|---------:|
| **Gemma 4** |     $0.00  |      $0.00  |  $0.00  |   yes    |
| Minimax M2.7|     $1.60  |      $0.36  |  $1.96  |   yes    |
| GLM-5.1     |     $2.40  |      $0.44  |  $2.84  |   yes    |
| Sonnet 4.6  |    $12.00  |      $3.00  | $15.00  |   yes    |
| Opus 4.6    |    $60.00  |     $15.00  | $75.00  |   overkill |

Recommended: Gemma 4 local — classification with a fixed 5-label schema is trivial for on-device models and costs nothing.

Anti-patterns

  • Don't recommend Opus by default "just to be safe". If Sonnet can do it, say so.
  • Don't recommend a local model for agentic tool-use loops — they spiral.
  • Always flag prices as approximate.

Example invocations

  • /model-cost-compare classify 10k support tickets into 5 buckets
  • "What's the cheapest model that can draft 200 SEO meta descriptions a day?"
  • "Should I use Opus or Sonnet for this 800k-token codebase review?"

© mergisi, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in skills/claude/model-cost-compare of mergisi/awesome-openclaw-agents.

Open the folder on GitHubat commit 05820c5

Compare with similar skills

Model Cost Compare next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Model Cost Compare compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Model Cost Compare this skillmergisi/awesome-openclaw-agents4k—~1kAutomated safety check: PassMIT
LLM Council on Fireworks AIdair-ai/dair-academy-plugins614—~5kAutomated safety check: NotesMIT
Model Architecture Diagram FinderBBuf/AI-Infra-Auto-Driven-SKILLS925—~1.2kAutomated safety check: PassNone
Image Genopen-octo/octo-agent125—~3.1kAutomated safety check: NotesMIT
Baoyu Image GenJimLiu/baoyu-skills26k1 repos~5.3kAutomated safety check: NotesMIT
Baoyu Imagineguanyang/open-agent-hub977—~4.6kAutomated safety check: NotesMIT

Similar skills

  • LLM Council on Fireworks AI

    dair-ai/dair-academy-plugins

    Has several open-weight models answer a question, rank each other's anonymized answers, then lets a chairman model write the final response through Fireworks AI.

    614 GitHub stars~5k tokensUpdated 2 mo ago
    AI & LLM EngineeringAuto-check: notes

  • Model Architecture Diagram Finder

    BBuf/AI-Infra-Auto-Driven-SKILLS

    Looks up public original architecture diagrams for named LLM, vision-language, MoE, diffusion and OCR models and returns the image with its source attribution.

    925 GitHub stars~1.2k tokensUpdated 4 days ago
    AI & LLM EngineeringAuto-check passed

  • Image Gen

    open-octo/octo-agent

    Acquire images as files — generate them with an AI image model (14 providers: OpenAI/gpt-image, Gemini, Qwen, Zhipu, Volcengine, Stability, FLUX, Ideogram, MiniMax, and more), search openly-licensed…

    125 GitHub stars~3.1k tokensUpdated today
    Media & CreativeAuto-check: notes

  • Baoyu Image Gen

    JimLiu/baoyu-skills

    AI image generation with OpenAI GPT Image 2.5, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream, Replicate and Agnes APIs.

    26k GitHub starsUsed in 1 repo~5.3k tokens
    Media & CreativeAuto-check: notes

  • Baoyu Imagine

    guanyang/open-agent-hub

    AI image generation with OpenAI GPT Image 2, Azure OpenAI, Google, OpenRouter, DashScope, Z.AI GLM-Image, MiniMax, Jimeng, Seedream and Replicate APIs.

    977 GitHub stars~4.6k tokensUpdated yesterday
    Media & CreativeAuto-check: notes

  • Quota Axi

    kunchenguid/quota-axi

    Report local Claude, Codex, Cursor, GitHub Copilot, Grok, Kimi, Z.AI, Alibaba, OpenCode Go, Antigravity, Command Code, MiniMax, MiMo, DeepSeek, OpenRouter, ElevenLabs, Devin, Muse, and Higgsfield…

    146 GitHub stars~547 tokensUpdated today
    Backend & APIsAuto-check passed

More from mergisi/awesome-openclaw-agents

All 16 skills in this repo

  • Claude Code Cost Optimizer

    mergisi/awesome-openclaw-agents

    Audits a project's Claude Code setup for common token-cost leaks and returns a prioritized fix list, using only static inspection of files and settings.

    4k GitHub stars~1.1k tokensUpdated 13 days ago
    Auto-check passed

  • Excalidraw Architecture Diagram

    mergisi/awesome-openclaw-agents

    Generates or updates a whiteboard-style architecture diagram of the current codebase as an Excalidraw JSON file, showing services and data flow.

    4k GitHub stars~1.1k tokensUpdated 13 days ago
    Auto-check passed

  • Git Commit Message Writer

    mergisi/awesome-openclaw-agents

    Drafts a commit message from your staged diff, matching the repo's own style and explaining why the change happened, not just what changed.

    4k GitHub stars~664 tokensUpdated 13 days ago
    Auto-check passed

  • Openclaw Debugger

    mergisi/awesome-openclaw-agents

    Trigger when an OpenClaw agent is broken, silent, crashing, stuck, not responding, returning empty output, or the user says "my agent is down", "agent not working", "/openclaw-debugger".

    4k GitHub stars~959 tokensUpdated 13 days ago
    Auto-check passed

  • Code Explainer

    mergisi/awesome-openclaw-agents

    Explains a pasted code snippet in plain English, returning the detected language, a one-sentence summary, how it works and one practical tip.

    4k GitHub stars~283 tokensUpdated 13 days ago
    Auto-check passed

  • Commit Message

    mergisi/awesome-openclaw-agents

    Generate a clean, conventional commit message from a description of your changes.

    4k GitHub stars~239 tokensUpdated 13 days ago
    Auto-check passed

Works with

Categories

Questions about Model Cost Compare

What does Model Cost Compare do?

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 is an agent skill from mergisi/awesome-openclaw-agents. 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".

When should I use Model Cost Compare?

Model Cost Compare fits situations like: the user asks which model to use; wants to compare model costs; says whats cheapest for this task; should I use Opus.

How do I install Model Cost Compare in Claude Code?

Run `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -a claude-code`. Or copy the skill folder (skills/claude/model-cost-compare in mergisi/awesome-openclaw-agents) into .claude/skills/model-cost-compare in your project. Claude Code loads it when a task matches its description.

How do I install Model Cost Compare in Codex?

Run `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -a codex`. Or copy the skill folder (skills/claude/model-cost-compare in mergisi/awesome-openclaw-agents) into .agents/skills/model-cost-compare in your project. Codex loads it when a task matches its description.

Can I use Model Cost Compare in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mergisi/awesome-openclaw-agents --skill model-cost-compare -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-cost-compare, .gemini/skills/model-cost-compare, .github/skills/model-cost-compare and .opencode/skills/model-cost-compare in your project.

What does Model Cost Compare need to run?

SKILL.md names no scripts, command-line tools or credentials: Model Cost Compare is instructions for the agent only.

Does Model Cost Compare access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Model Cost Compare safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Model Cost Compare use?

Model Cost Compare is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Model Cost Compare use?

About 1k tokens (SKILL.md is roughly 4.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Model Cost Compare?

Skills that share tags, products or a category with Model Cost Compare: LLM Council on Fireworks AI (dair-ai/dair-academy-plugins, 614 stars), Model Architecture Diagram Finder (BBuf/AI-Infra-Auto-Driven-SKILLS, 925 stars), Image Gen (open-octo/octo-agent, 125 stars) and Baoyu Image Gen (JimLiu/baoyu-skills, 26k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Model Cost Compare?

mergisi (a GitHub user) maintains it in mergisi/awesome-openclaw-agents, which has 3,999 GitHub stars. The repository holds 16 skills in this directory. The repository was last updated on September 26, 2026.

Source: mergisi/awesome-openclaw-agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.