free-coding-models
CLI tool that finds the fastest free coding LLM models by pinging 158 models across 20 providers in real-time. Displays live latency, uptime, stability, and quota usage in an interactive TUI. Ranks models by SWE-bench scores, provides continuous monitoring every 3 seconds, and includes a local reverse proxy for multi-account aggregation.
Score Breakdown
⚙ Agent Friendliness
🔒 Security
Good local secret handling (0600 permissions, masked display). Connects to 20 external providers over HTTPS. Config file contains multiple API keys — single point of compromise. MIT license.
⚡ Reliability
Best When
You want to find and monitor the fastest available free coding models across many providers.
Avoid When
You have a paid API subscription with sufficient capacity or need offline operation.
Use Cases
- • Finding the fastest available free coding model across 20 providers in real-time
- • Monitoring uptime and latency of free-tier AI model providers
- • Aggregating multiple free API accounts via local reverse proxy for higher throughput
Not For
- • Production API routing — this is a discovery and monitoring tool
- • Users with paid API subscriptions who do not need free-tier optimization
- • Offline environments — requires internet access to ping providers
Interface
Authentication
API keys for 20 providers stored in ~/.free-coding-models.json with 0600 permissions. Environment variable overrides supported. Setup wizard walks through each provider.
Pricing
Tool is free. Some providers require accounts (free signup). ZAI requires paid Coding Plan.
Agent Metadata
Known Gotchas
- ⚠ No MCP server or API — purely a human-facing CLI/TUI tool, not agent-accessible
- ⚠ Monitors 20 external providers — any provider can change their free tier without notice
- ⚠ Reverse proxy (fcm-proxy) is experimental for multi-account aggregation
- ⚠ Free tier limits vary wildly across providers and may change at any time
- ⚠ SWE-bench rankings may not reflect actual coding task performance for specific use cases
Full Evaluation Report
Comprehensive deep-dive: security analysis, reliability audit, agent experience review, cost modeling, competitive positioning, and improvement roadmap for free-coding-models.
AI-powered analysis · PDF + markdown · Delivered within 30 minutes
Package Brief
Quick verdict, integration guide, cost projections, gotchas with workarounds, and alternatives comparison.
Delivered within 10 minutes
Score Monitoring
Get alerted when this package's AF, security, or reliability scores change significantly. Stay ahead of regressions.
Continuous monitoring
Scores are editorial opinions as of 2026-03-08.