free-coding-models

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

What is free-coding-models?

Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time

Overview of free-coding-models

What it is

free-coding-models is a command-line tool that finds, benchmarks, and installs over 170 free coding LLM models from more than 15 providers in real time. It pings every model in parallel, displays live latency, and computes a live Stability Score (0-100) based on p95 latency, jitter, spike rate, and uptime. The tool can write the selected model directly into a coding tool's configuration and launch that tool. It works with OpenCode CLI, Desktop, WebUI, OpenClaw, Crush, Goose, Aider, Kilo CLI, Qwen Code, OpenHands, Amp, Hermes, Continue, Cline, Xcode, Pi, ZCode, ForgeCode, Copilot, jcode, Caveman Code, and more. The project is created by Vanessa Depraute (Vava-Nessa).

Key features

  • Live latency and stability rankings for 257 models from 25 free AI providers.
  • Interactive Terminal UI (TUI) with live sortable table, one-key launch into coding tools.
  • Web Dashboard browser control center with shareable filtered views, Docker-ready.
  • Agent Extensions for OpenCode and Pi plugins for hot-swapping models mid-session.
  • Smart Model Router: a local OpenAI-compatible daemon with auto-failover.
  • AI Speed Test benchmarks measuring real completions, AI latency, and tokens per second.
  • Smart Recommend three-question wizard for top picks.
  • Persistent 24-hour probe cache shared by all surfaces.
  • Live quota display from response headers.
  • Real-world telemetry scores and models.dev enrichment with drift detection.
  • Tier scale based on SWE-bench Verified (S+ ≥ 70% down to C).

Use cases

  • Developers who want to quickly find the fastest free coding model for their current task.
  • Users who need to benchmark multiple free AI providers and models in real time.
  • Teams that want to integrate a reliable free model into their coding toolchain with minimal setup.
  • Anyone exploring free-tier AI coding models across providers like Groq, Cerebras, NVIDIA NIM, and others.

Getting started

bash npm install -g free-coding-models free-coding-models --help Then create a free account on one of the 25 providers to grab an API key. Launch the tool with free-coding-models and paste your key on first run.

License and pricing

The license is not stated. The project is listed as open source on GitHub. The tool itself is free to use; models are free as defined by each provider (permanent free tier, :free variant, or free plan).

Based on the project's public README and repository metadata.

Add this badge to your README

Featured on YunoDB Badge styles & help

Maintain this project? Show that it is featured on YunoDB.

Markdown[![Featured on YunoDB](https://yunodb.com/badge/vava-nessafree-coding-models.svg)](https://yunodb.com/tools/vava-nessafree-coding-models?utm_source=github&utm_medium=badge)
HTML<a href="https://yunodb.com/tools/vava-nessafree-coding-models?utm_source=github&utm_medium=badge"><img src="https://yunodb.com/badge/vava-nessafree-coding-models.svg" alt="Featured on YunoDB" height="20"></a>