npm install -g free-coding-models
free-coding-models
💡 Why this tool?
There is a large catalog of free and free-limited coding models (25 providers / 257 live models, generated from sources.js). Which one is fastest right now? Which one is actually stable, versus just lucky on the last ping?
free-coding-models (FCM) answers that by pinging every model in parallel, showing live latency, and computing a live Stability Score (0-100) combining p95 latency, jitter, spike rate and uptime. Average latency alone is misleading: a model that randomly spikes to 6 seconds is not reliable.
Once you pick a model, FCM writes it directly into your coding tool's config and opens the tool, so you go from "which model?" to "coding" in under 10 seconds.
| Surface | What it is | Docs |
|---|
| 🎛️ TUI | The interactive terminal dashboard. The default: live ranking, pick + launch. | docs/tui.md |
| 🌐 Web Dashboard | Browser control center, shareable filtered views, Docker-ready. | docs/web-dashboard.md |
| 🔌 Agent Extensions | OpenCode & Pi plugins: hot-swap models mid-session. | Agent extensions |
| 🔀 Smart Model Router | A local OpenAI-compatible daemon with auto-failover. | docs/router.md |
Other highlights: AI Speed Test benchmarks (real completions, AI Latency + TPS), Smart Recommend (3-question wizard), a Ctrl+P Command Palette, a persistent 24h probe cache shared by every surface, live quota from response headers, real-world telemetry scores, models.dev enrichment with drift detection, and a tier scale based on SWE-bench Verified (S+ ≥ 70% down to C). Details: docs/stability.md.
⚡ Quick Start
① Install (Node.js 18+, no native build, never needs sudo):
npm install -g free-coding-models
free-coding-models --help # prints every flag
② Grab one free API key. One is enough to start; add more later with P inside the app:
③ Launch & paste your key: free-coding-models. First run prompts for keys (Enter skips), models ping in parallel, rows light up green ✅.
④ Pick a model & launch your tool: ↑↓ navigate, Enter to write the model into your tool's config and launch it. Pre-target another tool from the CLI, or cycle live with Z:
free-coding-models --goose --tier S # Goose, pre-filtered to S-tier only
free-coding-models --crush --origin groq # Crush, Groq models only
free-coding-models --fiable # print the single most reliable model and exit
⑤ Go further:
🟢 Providers
24 active providers / 258 live models, sorted by live model count. Top 8:
🧾 What "free" means here: free is a property of the (provider, model) pair, never of the provider as a whole. A row is listed only when that exact model id costs $0 to call through that provider (permanent free tier, :free variant, or free plan), verified live at audit time. The same open-weights model can be free on one host and paid on another - paid siblings are deliberately excluded. Full breakdown and badge legend: docs/providers.md.
📖 Full table, free-tier limits, env vars, tier scale and provider notes: docs/providers.md (generated from sources.js by node scripts/generate-provider-table.mjs, so counts cannot drift). OpenCode Zen's free models are listed there too.
⚠️ Health probes consume provider quota: FCM auto-pauses a provider on 429, backs off exponentially per failing model, and shows a footer chip while a provider rests. Leave a key empty and anonymous liveness probes still work for most providers.
🧩 Your own providers (Ollama, LM Studio, vLLM, private gateways)
Any OpenAI-compatible endpoint can be added to ~/.free-coding-models.json under customProviders (issue #197). Custom models are pinged, scored, filtered, routable through the Smart Router, installable into your coding tools, and visible on the Web Dashboard, exactly like built-in providers:
{
"customProviders": {
"ollama-local": {
"name": "Ollama Local",
"url": "http://localhost:11434/v1/chat/completions",
"quota": "Local, unlimited",
"quotaCode": "free",
"models": [
["qwen3-coder:30b", "Qwen3 Coder 30B", "A", "-", "262k"],
["llama4:70b"]
]
},
"vllm-gpu": {
"url": "https://gpu.internal:8000/v1/chat/completions",
"envVar": "VLLM_API_KEY",
"models": [["deepseek-v4.1", "DeepSeek V4.1", "S", "-", "128k"]]
}
}
}
This is the beginning of the README. Read the rest at the original. Read the full README ↗
