Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
AI coding tools that give free Claude Opus/Sonnet, GPT-5, Gemini Pro, and other pro-grade models
| Date | Stars |
|---|---|
| 2026-07-31 | 755 |
| 2026-08-03 | 755 |
| 2026-08-06 | 755 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
Last updated: December 5, 2025 • PRs/issues welcome **Languages:** [Español](README-es.md) • [Português](README-pt-BR.md) • [中文](README-zh.md) • [Français](README-fr.md) • [日本語](README-ja.md) • [हिन्दी](README-hi.md) • [Deutsch](README-de.md) # AI Coding Tools: Where Pro-Grade Models Are Actually Free Many AI coding tools claim to be "free," but access to pro-grade models usually runs out fast, then you're downgraded. Each tool uses different limits (credits, tokens, requests), making comparison difficult. This list puts them side by side to show what you actually get for free. ## TL;DR — Free Tiers for Pro‑Grade AI Coding (tools with higher limits listed first) | Tool | Pro‑grade models | Free tier limit | Credit card | |------|------------------|------------------|-------------| | [Qwen Code](https://github.com/QwenLM/qwen-code) | Qwen3-Coder-480B | 2,000 requests/day | No | | [Rovo Dev CLI](https://www.atlassian.com/blog/announcements/rovo-dev-command-line-interface) | Claude Sonnet 4 | 5M tokens/day (beta) | No | | [Gemini CLI](https://github.com/google-gemini/gemini-cli) | Gemini 3 Pro, Gemini 2.5 Pro | Gemini 3 Pro (waitlist/paid), 100 req/day Gemini 2.5 Pro | No | | [Cursor](https://cursor.com/) | GPT-5.1-Codex-Max | Free until Dec 11, 2025 (77.9% SWE-bench) | No | | [Kilo Code](https://kilocode.ai/) | Claude Opus/Sonnet, Gemini 2.5 Pro, GPT‑4.1 | Up to $25 signup credits (one‑time) | Yes | | [Warp](https://warp.dev/) | GPT‑5, Claude Opus 4.1, Claude Sonnet 4, Gemini 2.5 Pro | 150 credits/month (first 2 months), then 75/month | No | | [Trae](https://trae.ai/) | Claude 4 Sonnet (Beta), Claude 3.7 Sonnet, GPT‑4.1, GPT‑4o, Gemini 2.5 Pro | 10 fast + 50 slow requests/month | No | | [Amazon Q Developer](https://aws.amazon.com/q/developer/) | Claude Sonnet 4 | 50 agentic requests/month | Yes | | [GitHub Copilot](https://github.com/features/copilot/plans) | GPT‑4.1, Claude Opus 3.5, Gemini 2.0 Flash, Grok Code Fast 1 | 50 chat requests + 2,000 completions/month | No | | [Windsurf](https://windsurf.com/) | OpenAI, Anthropic, Google, xAI | 25 credits/month | Yes | | [Jules](https://jules.google/) | Gemini 2.5 Pro | 15 tasks/day | No | | [AWS Kiro](https://kiro.dev/) | Claude 4 Sonnet, Claude 3.7 Sonnet | 50 credits/month | No | | [Qoder](https://qoder.com/) | Qwen3-Coder-480B, Claude, GPT, Gemini | Free tier + 2-week Pro trial (1,000 credits) | No | ### Qualifying Pro‑Grade Models Only models achieving >60% on SWE-bench Verified qualify as pro-grade for real-world coding tasks. Below is the current list | Model | SWE-bench Verified | Provider | |-------|-------------------|----------| | Claude Opus 4.5 | 80.9% | Anthropic | | GPT-5.1-Codex-Max | 77.9% | OpenAI | | Claude Sonnet 4.5 | 77.2% (82.0% w/ parallel) | Anthropic | | Gemini 3 Pro | 76.2% | Google | | GPT-5 | 74.9% | OpenAI | | Claude Opus 4.1 | 74.5% | Anthropic | | Claude Sonnet 4 | 72.7% (80.2% w/ parallel) | Anthropic | | GPT-5 mini | 71.0% | OpenAI | | Qwen3-Coder-480B | 69.6% (interactive) / 67.0% (single) | Alibaba | | Gemini 2.5 Pro | 63.2% | Google | ### Contributing If you spot an error, missing source link, or have updated quota/model information, please open an issue or pull request with a source. New tool contributions are welcomed! See CONTRIBUTING.md for detailed guidelines. ### Disclaimer No affiliation with any vendor. All trademarks belong to their owners. Information is for research; accuracy not guaranteed; limits/pricing change frequently. ## Contents - [1. AI-coding Tools with Free Access to Pro-Grade Models](#1-ai-coding-tools-with-free-access-to-pro-grade-models) - [2. API Providers for AI Coding Tools](#2-api-providers-for-ai-coding-tools) - [3. Tools with Paid Tiers with Pro-Grade Models](#3-tools-with-paid-tiers-with-pro-grade-models) - [4. Tools with Free Access to Basic Models](#4-tools-with-free-access-to-basic-models) - [5. Local Models](#5-local-models) - [Comparison Notes](#comparison-notes) - [Related Resources](#related-res
Excerpt of 25,907 characters
Read on GitHub
120
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:6348acccafc1cac9, topic:code-generation, topic:coding-assistant
matched fp:6348acccafc1cac9, topic:llm
matched fp:6348acccafc1cac9, topic:awesome-list