Find the fastest free coding model in seconds
_{Ping 174 models across 23 AI Free providers in real-time
Install Free API endpoints to your favorite AI coding tool:
📦 OpenCode, 🦞 OpenClaw, 💘 Crush, 🪿 Goose, 🛠 Aider, 🐉 Qwen Code, 🤲 OpenHands, ⚡ Amp, π Pi, 🦘 Rovo or ♊ Gemini in one keystroke}

npm install -g free-coding-models
free-coding-models

create a free account on one of the providers

Why • Quick Start • Providers • Usage • TUI Keys • Contributing

_{Made with ❤️ and ☕ by Vanessa Depraute (aka Vava-Nessa)}

There are 174+ free coding models scattered across 23 providers. Which one is fastest right now? Which one is actually stable versus just lucky on the last ping?

This CLI pings them all in parallel, shows live latency, and calculates a live Stability Score (0-100). Average latency alone is misleading if a model randomly spikes to 6 seconds; the stability score measures true reliability by combining p95 latency (30%), jitter/variance (30%), spike rate (20%), and uptime (20%).

It then writes the model you pick directly into your coding tool's config — so you go from "which model?" to "coding" in under 10 seconds.

Create a free account on one provider below to get started:

174 coding models across 23 providers, ranked by SWE-bench Verified.

💡 One key is enough. Add more at any time with P inside the TUI.

① Install and run:

npm install -g free-coding-models
free-coding-models

On first run, you'll be prompted to enter your API key(s). You can skip providers and add more later with P.

Use ⚡️ Command Palette! with Ctrl+P.

Need to fix contrast because your terminal theme is fighting the TUI? Press G at any time to cycle Auto → Dark → Light. The switch recolors the full interface live: table, Settings, Help, Smart Recommend, Feedback, and Changelog.

② Pick a model and launch your tool:

↑↓ navigate   →   Enter to launch

The model you select is automatically written into your tool's config (📦 OpenCode, 🦞 OpenClaw, 💘 Crush, etc.) and the tool opens immediately. Done.

If the active CLI tool is missing, FCM now catches it before launch, offers a tiny Yes/No install prompt, installs the tool with its official global command, then resumes the same model launch automatically.

💡 You can also run free-coding-models --goose --tier S to pre-filter to S-tier models for Goose before the TUI even opens.

# "I want the most reliable model right now"
free-coding-models --fiable

# "I want to configure Goose with an S-tier model"
free-coding-models --goose --tier S

# "I want NVIDIA's top models only"
free-coding-models --origin nvidia --tier S

# "Start with an elite-focused preset, then adjust filters live"
free-coding-models --premium

# "I want to script this — give me JSON"
free-coding-models --tier S --json | jq -r '.[0].modelId'

# "I want to configure OpenClaw with Groq's fastest model"
free-coding-models --openclaw --origin groq

Press Z in the TUI to cycle between tools without restarting.

🦘 Rovo Dev CLI

• Provider: Atlassian Rovo
• Install: Installation Guide
• Free tier: 5M tokens/day (beta, requires Atlassian account)
• Model: Claude Sonnet 4 (72.7% SWE-bench)
• Launch: free-coding-models --rovo or press Z until Rovo mode
• Features: Jira/Confluence integration, MCP server support

♊ Gemini CLI

• Provider: Google Gemini
• Install: npm install -g @google/gemini-cli
• Free tier: 1,000 requests/day (personal Google account, no credit card)
• Models: Gemini 3 Pro (76.2% SWE-bench), Gemini 2.5 Pro, Gemini 2.5 Flash
• Launch: free-coding-models --gemini or press Z until Gemini mode
• Features: OpenAI-compatible API support, MCP server support, Google Search grounding

Note: When launching these tools via Z key or command palette, if the current mode doesn't match the tool, you'll see a confirmation alert asking to switch to the correct tool before launching.

OpenCode Zen is a hosted AI gateway offering 8 free coding models exclusively through OpenCode CLI and OpenCode Desktop. These models are not available through other tools.

To use Zen models: sign up at opencode.ai/auth and enter your Zen API key via P (Settings). Zen models appear in the main table and auto-switch to OpenCode CLI on launch.

When a tool mode is active (via Z), models incompatible with that tool are highlighted with a dark red background so you can instantly see which models work with your current tool.

→ Full flags reference

→ Stability score & column reference

• Parallel pings — all 174 models tested simultaneously via native fetch
• Adaptive monitoring — 2s burst for 60s → 10s normal → 30s idle
• Stability score — composite 0–100 (p95 latency, jitter, spike rate, uptime)
• Smart ranking — top 3 highlighted 🥇🥈🥉
• Favorites — star models with F, persisted across sessions, default to normal rows, and switch display mode with Y (pinned+sticky vs normal rows)
• Configured-only default — only shows providers you have keys for
• Keyless latency — models ping even without an API key (show 🔑 NO KEY)
• Smart Recommend — questionnaire picks the best model for your task type
• ⚡️ Command Palette — Ctrl+P opens a searchable action launcher for filters, sorting, overlays, and quick toggles
• Install Endpoints — push a full provider catalog into any tool's config (from Settings P or ⚡️ Command Palette)
• Missing tool bootstrap — detect absent CLIs, offer one-click install, then continue the selected launch automatically
• Tool compatibility matrix — incompatible rows highlighted in dark red when a tool mode is active
• OpenCode Zen models — 8 free models exclusive to OpenCode CLI/Desktop, powered by the Zen AI gateway
• Width guardrail — shows a warning instead of a broken table in narrow terminals
• Readable everywhere — semantic theme palette keeps table rows, overlays, badges, and help screens legible in dark and light terminals
• Global theme switch — G cycles auto, dark, and light live without restarting
• Auto-retry — timeout models keep getting retried

We welcome contributions — issues, PRs, new provider integrations.

Q: How accurate are the latency numbers?
A: Real round-trip times measured by your machine. Results depend on your network and provider load at that moment.

Q: Can I add a new provider?
A: Yes — see sources.js for the model catalog format.

→ Development guide · Config reference · Tool integrations

GitHub Issues · Discord

MIT © vava

Contributors

_{vava-nessa · erwinh22 · whit3rabbit · skylaweber · PhucTruong-ctrl}

_{Anonymous usage data collected to improve the tool. No personal information ever.}