model-picker
Find the cheapest AI model that is smart enough for a task, and the cheapest provider to run it on, from live Artificial Analysis benchmarks via Firecrawl. Use when the user asks which model to use, how to cut their LLM or API bill, whether a cheaper model would do, which provider is cheapest or fastest for a model, which open-weights model to self-host, or wants something built with the cheapest model for each step.
含まれるファイル（1）
- SKILL.md2.8 KB
SKILL.md（原文）
インストールする前に、エージェントに与えられる指示の中身を確認できます。
Model picker
The CLI is model-picker. If it isn't on PATH, ask the user to install it with curl -fsSL https://raw.githubusercontent.com/firecrawl/model-picker/main/install.sh | sh, or run bun src/cli.ts from two directories above this skill's base directory instead (after bun install there). It needs FIRECRAWL_API_KEY (free at https://firecrawl.dev), from the environment or ~/.config/model-picker/.env; if a command says a key is missing, ask the user to run mp setup in their own terminal (it prompts for keys, so don't run it yourself). Results are cached for 24 hours, so repeat runs cost nothing.
1. Turn the task into a score floor
Scores are the Artificial Analysis Intelligence Index (0-100; the best models score about 55-58).
| Task | --min-score |
|---|---|
| Hard agentic coding, multi-step research, long autonomous runs | 50 |
| Everyday coding, writing, analysis, tool use | 42 |
| Summaries, extraction, classification, routing | 30 |
If the user names the model they use today, pass it with --vs <slug>; find slugs with search <name>.
2. Pick the model
model-picker pick --min-score 42 --vs claude-fable-5-1
model-picker pick --min-score 35 --open # self-hostable only
model-picker pick --min-score 42 --max-cost 0.5
Each row is a model nothing else beats on both score and cost, cheapest first. Recommend the cheapest row that clears the floor, and say what the user gives up versus their current model (the vs column).
3. Pick the provider
model-picker providers <slug> # cheapest first
model-picker providers <slug> --sort speed
Cost per task includes how many tokens each provider's setup actually burns, so it can rank providers differently from list prices.
4. Build with the cheapest model per step
When the user wants something built cheaply, rather than just a recommendation:
model-picker build "<task>" --dir <folder>
A capable model writes plan.json, then each step runs in OpenCode on the cheapest model good enough for its difficulty, in parallel where steps don't share files. It needs OpenCode on the PATH and OPENROUTER_API_KEY, and spends real money on that key, so confirm with the user first. Afterwards, show them <folder>/REPORT.md: each step's model, time, tokens and cost, plus a per-model breakdown.
Add --json to pick, providers and search to read the numbers programmatically.
レビュー
まだレビューはありません。使ってみた感想をお寄せください。