Automated summary

Queries the live models.dev catalog through the tokenomics CLI or its MCP server to retrieve current LLM pricing and estimate or compare costs.

Strengths

Always-live pricing with no local database or cache to refresh
JSON output plus --fields keeps responses small and cheap to parse
compare/compare_models performs the cost math instead of leaving it to the agent
Read-only MCP tools, each returning a verifiable fetched_at timestamp

Limitations

Assumes the tokenomics CLI or MCP server is already installed and reachable in the environment
Prices are only expressed in USD per million tokens, not other currencies
Does not tokenize text for you: you must supply raw token counts

When to use it

Use it whenever you need current LLM prices, a cost estimate, or a cheap-vs-expensive decision across models for a specific workload.

When not to use it

Avoid it for counting tokens in an actual prompt or for offline work, since there is no local data or cache.

Security analysis

Safe

Quality score86/100

The skill only documents read-only pricing lookups via a tokenomics CLI/MCP server against models.dev. It does not instruct installing software, piping remote scripts, deleting files, accessing credentials, or exfiltrating data. The supplied commands are benign examples for querying model prices and cost estimates.

No concerns found

How this analysis is made

Examples

Compare two models for a workload

Compare the cost of openai/gpt-4o and google/gemini-2.5-flash for 1,000,000 input tokens and 500,000 output tokens, and tell me which is cheaper.

Find cheap models by price

Search tokenomics for models with 'gpt' in the name whose input price is at most $1 per million tokens, and show only model_id and pricing.

Estimate a batch cost

Estimate what 10 requests of 1,000,000 input tokens and 200,000 output tokens would cost on openai/gpt-4o.

name: tokenomics description: Get fresh, live LLM pricing and cost estimates via the tokenomics CLI or MCP server.

tokenomics — live LLM pricing for agents

Name: Tokenomics - Live LLM Pricing
Author: Skills Guide Bot

Prices come live from the models.dev catalog (thousands of models across 140+ providers). There is no local database and no cache to refresh — every call reflects current data.

Units (read this first)

All token prices are USD per 1,000,000 tokens. A value of 2.5 means $2.50 per 1M tokens.
estimate/estimate_cost take raw token counts (e.g. 1000000), not millions.
output_per_mtok: null means the model is non-generative (embeddings/rerankers); output tokens cost $0.

Rules

Use --output json (or rely on the default: JSON whenever output is piped) and parse it.
Add --fields a,b,c to every search to keep responses small (masks the rows under models).
Resolve real model ids with search before get/estimate. Model ids are provider/model, e.g. openai/gpt-4o.
For "which is cheaper for my workload", use compare / compare_models — it does the math; don't compute prices yourself.
Model and provider ids are plain identifiers: no ?, #, %, /-prefixed paths, or query params.
On MODEL_NOT_FOUND, read details.suggestions or run search; do not invent ids.

CLI quickstart

tokenomics search "gpt" --max-input 1 --fields model_id,pricing --output json
tokenomics get openai/gpt-4o
tokenomics estimate openai/gpt-4o --input-tokens 1000000 --output-tokens 200000 --requests 10
tokenomics compare --models openai/gpt-4o,google/gemini-2.5-flash --input-tokens 1000000 --output-tokens 500000
tokenomics providers
tokenomics schema estimate   # JSON Schema for any command's input

MCP tools

search_models, get_model_pricing, estimate_cost, compare_models — all read-only. Each returns JSON with fetched_at. No write/refresh tool exists because data is always live.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/tokenomics-live-llm-pricing-mrx3y0sw/download' --output '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md.part' && mv '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md.part' '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && test -s '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/tokenomics' && cp -R '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw' '.claude/skills/tokenomics'

Cursor

test -f '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && test -s '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/tokenomics' && cp -R '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw' '.cursor/skills/tokenomics'

Codex

test -f '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && test -s '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/tokenomics' && cp -R '.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw' '.agents/skills/tokenomics'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw'

openskills read 'tokenomics-live-llm-pricing-mrx3y0sw'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/tokenomics-live-llm-pricing-mrx3y0sw/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot