Free AI coding got a lot less free in 2026. Gemini CLI dropped its famous 1,000-requests-a-day free tier. Qwen Code ended its free login. GitHub Models shut down. Roo Code closed and Continue stopped development. Cerebras turned its free tier into a 30-day trial. Since our last check, Hugging Face stopped giving free accounts monthly credit and Ollama Cloud's free plan became pay as you go. Most "free AI coding" lists online still recommend all of them.
This page is the corrected version. It lists the coding agents that are still free to use, the free model APIs you can plug into them, and the real published limits for each. Every number below was checked on the provider's own pricing, docs or rate-limit page on October 29, 2026. Where a provider does not publish its limits, we say so.
Free AI coding agents at a glance
Every agent on this page in one table. "Free limit" is what you get without paying anything. "Bring your own key" means you can plug in a free API from the second table below.
Tap any name in the table to jump to its full entry below.
| Agent | Where it runs | Open source | Free limit | Bring your own key | Paid plan from |
|---|---|---|---|---|---|
| opencode | Terminal, desktop app | Yes (MIT) | 10 free Zen models (limited time), no published cap | Yes, 75+ providers | Go $10/mo |
| Cline | VS Code, JetBrains, CLI | Yes (Apache-2.0) | Tool is free, limits come from your model | Yes | Pay per model use |
| Kilo Code | VS Code, JetBrains, CLI | Yes (MIT) | Free models on its gateway, where available | Yes | Kilo Pass $19/mo |
| Antigravity CLI | Terminal | No | Gemini 3.8 Flash and more, weekly limits (not published) | No | Google AI Pro |
| Goose | Desktop app, CLI | Yes (Apache-2.0) | Tool is free | Yes, 15+ providers | None |
| Zed | Editor | Yes (GPL-3.0) | Unlimited agent use with your own keys or external agents | Yes | Pro $10/mo |
| GitHub Copilot Free | VS Code, JetBrains, GitHub | No | 2,000 completions/mo, limited chat and agent use | Limited | Pro $10/mo |
| Kiro | Desktop IDE | No | 50 credits/mo | No | Pro $20/mo |
| Cursor Free | Desktop IDE | No | "Limited agent requests" (not published) | Not confirmed | Plus $8/mo (Grok models only) |
| Devin Desktop (was Windsurf) | Desktop IDE | No | "Light quota" (not published) | Not mentioned | Pro $20/mo |
| Mistral Vibe | Terminal, IDE, web | Yes (Apache-2.0) | Limited coding sessions on the free Mistral plan | Mistral API key | Pro $14.99/mo |
| Crush | Terminal | Source available (FSL) | Tool is free | Yes | None |
| Claude Code | Terminal, IDE, desktop | No | None (Pro plan needed), or free models via OpenRouter | Yes, via gateway | Pro $20/mo |
| Codex CLI | Terminal, IDE, desktop | Yes (Apache-2.0) | Desktop app only on ChatGPT Free, CLI needs Plus | API key | Plus $20/mo |
| Gemini CLI | Terminal | Yes (Apache-2.0) | None since June 18, 2026 | Paid API key only | Code Assist Standard |
What changed in 2026
| Tool or API | What happened | When |
|---|---|---|
| Gemini CLI | Stopped serving free users and Google AI Pro/Ultra. Free users moved to Antigravity CLI | June 18, 2026 |
| Qwen Code | Free Qwen OAuth tier ended | April 15, 2026 |
| Roo Code | Shut down, repo archived (community fork: ZooCode) | May 15, 2026 |
| Continue | Final 2.0.0 release, repo now read-only | June 2026 |
| GitHub Models | Free model playground and API retired | July 30, 2026 |
| Amazon Q Developer | No new free sign-ups, users pointed to Kiro | May 15, 2026 |
| Cerebras | Permanent free tier replaced by a $5, 30-day trial with a card | 2026 |
| Windsurf | Renamed Devin Desktop, free plan now a "light quota" | June 2026 |
| Antigravity | Claude Sonnet 4.6, Claude Opus 4.6 and GPT-OSS-120b removed from all plans, including free | November 2, 2026 (announced) |
Free AI coding agents
These are the agent apps themselves. Most are free and open source, and you pay only for the model, which can also be free (see the next section).
1. opencode
Terminal agent · TERMINAL
Our pick for free AI coding. opencode works with 75+ model providers and has its own Zen gateway, which currently offers ten free models, all marked limited time. They include Big Pickle, GLM-5.3-Flash Free, DeepSeek V4.1 Flash Free, MiMo-V2.6-Flash Free and Nemotron 3 Ultra Free. The free models work only inside opencode. If you outgrow them, the Go plan is $10 a month for about 30 models, including GLM-5.3, Kimi K3.1 Pro and DeepSeek V4 Pro, with rolling 5-hour, weekly and monthly allowances. It also reads Claude Code's CLAUDE.md and skills, so switching back and forth is painless.
Free limit: Zen free models, no published daily cap. Install: curl -fsSL https://opencode.ai/v2/install | bash.
- Replaces
- Claude Code, Codex
- Runs on
- Mac, Linux, Windows
- Difficulty
- Easy
- Licence
- MIT (open)
- Skip if
- You want one vendor's best model with no setup
2. Cline
VS Code agent · VS CODE
The most popular open source agent inside VS Code (about 71k GitHub stars). Cline's pricing page says the open source extension is completely free for individual developers, and you pay only for AI inference when you use a model. Pair it with OpenRouter free models, Groq or a local model through Ollama or LM Studio. It shows every file change and command for approval, which is reassuring when you are trying free models of uneven quality.
Free limit: the tool is free. Limits come from the model you connect.
- Replaces
- Cursor, Copilot agent mode
- Runs on
- VS Code, JetBrains, CLI
- Difficulty
- Easy
- Licence
- Apache-2.0 (open)
- Skip if
- You work only in the terminal
3. Kilo Code
VS Code + CLI agent · VS CODE
An open source agent with its own gateway that charges exact provider rates with no markup (there is a 5% fee when you buy credits). Its "Auto Free" option routes to free models on the gateway where they are available, and local models through Ollama or LM Studio cost nothing. The Kilo CLI is a fork of opencode and gets new builds almost daily.
Free limit: free extension and CLI, free models on the gateway when available. Paid Kilo Pass from $19 a month.
- Replaces
- Cursor
- Runs on
- VS Code, JetBrains, CLI
- Difficulty
- Easy
- Licence
- MIT (open)
- Skip if
- You already use Cline
4. Antigravity CLI
Terminal agent · GOOGLE
Google's replacement for Gemini CLI's free tier. The free individual plan uses Gemini 3.8 Flash, plus Claude Sonnet 4.6, Claude Opus 4.6 and GPT-OSS-120b, but Google says those three leave on November 2, 2026. After that, free users get Gemini 3.8 Flash only. Gemini 3.1 Pro is now listed for Enterprise only. Limits are "basic weekly rate limits" that Google does not put a number on. Tab completions are unlimited. The CLI command is agy, it supports skills, hooks and subagents, and it is on version 1.4.10.
Free limit: weekly, not published. Install: curl -fsSL https://antigravity.google/cli/install.sh | bash (Mac and Linux; Windows has a PowerShell installer).
- Replaces
- Gemini CLI
- Runs on
- Mac, Linux, Windows
- Difficulty
- Easy
- Licence
- Proprietary
- Skip if
- You need an open source tool
5. Goose
Desktop + CLI agent · TERMINAL
Started at Block and now part of the Linux Foundation's Agentic AI Foundation (AAIF), alongside MCP and AGENTS.md. Goose works with 15+ providers and can even drive your existing Claude, ChatGPT or Gemini subscription through the Agent Client Protocol (ACP). Strong MCP support, a desktop app for Mac, Linux and Windows, and a full CLI.
Free limit: free tool. Bring any model.
- Replaces
- Claude Code
- Runs on
- Mac, Linux, Windows
- Difficulty
- Easy
- Licence
- Apache-2.0 (open)
- Skip if
- You want a big plugin ecosystem
6. Zed
Editor with agent · EDITOR
A fast open source editor with a built-in agent panel. The free Personal plan gives unlimited agent use when you bring your own API keys or plug in external agents like Claude Agent or Codex CLI. Zed's own hosted models and its Zeta edit predictions are not included on the free plan, but you can use GitHub Copilot or a local model for predictions instead. Pro is $10 a month with unlimited edit predictions and $5 of tokens included.
Free limit: unlimited with your own keys or external agents. No Zed-hosted models.
- Replaces
- Cursor
- Runs on
- Mac, Linux, Windows
- Difficulty
- Easy
- Licence
- GPL-3.0 (open)
- Skip if
- You depend on VS Code extensions
7. GitHub Copilot Free
IDE assistant · IDE
Still free, still limited: 2,000 code completions a month, plus "limited chat and agent usage" from an allowance of AI Credits. GitHub no longer publishes a fixed number of free chat requests. Models are picked for you by automatic model selection. Copilot CLI and agent mode are included. Fine for occasional use, not for daily agent work. Pro is $10 a month.
Free limit: 2,000 completions a month, chat and agent use limited by AI Credits (amount not published).
- Replaces
- Paid Copilot
- Runs on
- VS Code, JetBrains, GitHub
- Difficulty
- Easy
- Licence
- Proprietary
- Skip if
- You need heavy agent use
8. Kiro
Agentic IDE · IDE
Amazon's agentic IDE, and where Amazon Q Developer users are being sent. The perpetual free tier gives 50 credits, reset each month, with Claude Sonnet 4.5 and open-weight models (Qwen3 Coder Next, DeepSeek 3.2 and MiniMax M2.1 for social-login and AWS Builder ID users). That is a taster, not a daily driver. Pro is $20 a month for 1,000 credits.
Free limit: 50 credits a month.
- Replaces
- Amazon Q Developer
- Runs on
- Mac, Linux, Windows
- Difficulty
- Easy
- Licence
- Proprietary
- Skip if
- You want unlimited free use
Other free agents
These are free to try, but each has a catch.
- Cursor Free: "limited agent requests" and "limited Chat requests", with no numbers published. Cursor's pricing has changed: the cheapest paid plan is now Plus at $8 a month with Grok models only, and third-party models start with Premium at $30 a month.
- Devin Desktop (formerly Windsurf): a "light quota" for agents, limited model choice, unlimited Tab completions and inline edits. Pro is $20 a month.
- Mistral Vibe: the free Mistral plan includes limited coding sessions. The open source Vibe CLI needs a Mistral API key, and Mistral's API has a free mode with no card. Pro is $14.99 a month with $15 of API credit.
- Crush from Charm: a free, polished terminal agent that takes your own keys or local models, but its FSL licence is source-available rather than open source.
- Claude Code: not included in Claude's free plan. It starts with Pro at $20 a month ($17 a month billed yearly), or you can route it to free models.
- Codex: ChatGPT Free includes Codex in the desktop app only (GPT-6 Luna, still rolling out). The CLI, IDE extension and web need Plus at $20 a month, or an API key.
- Aider still works but has not shipped a release since February 2026.
And if you already use Claude Code, you do not need a new agent at all: point it at free models and keep your setup. We walk through it in how to use Claude Code for free.
Free model APIs for coding: the quota table
This is the part that decides whether "free" actually works. Coding agents make many requests per task (reading files, running commands, retrying), so a limit of 20 requests a day runs out in one small feature.
| Provider | Free models for coding | Free limit (published) | Card needed? |
|---|---|---|---|
OpenRouter (:free models) | Rotating set. Now includes NVIDIA Nemotron 3 Ultra and 3.5, Gemma 4, Poolside Laguna and Cohere North Mini Code | 20 per minute. 50 per day, or 1,000 per day after buying $10 of credits once | No (yes for the 1,000/day tier) |
| Groq | gpt-oss-120b, gpt-oss-20b, Qwen 3.8 27B | 30 per minute, 1,000 per day, 8K tokens per minute, 200K tokens per day, per model | No |
| Google AI Studio (Gemini API) | Gemini 3.8 Flash, 3.6 Flash, 3.5 Flash-Lite, 3.1 Flash-Lite and 2.5 Pro (not 3.1 Pro) | Not published. Shown per account in AI Studio | No |
| opencode Zen | 10 free models, limited time, opencode only | Not published | No |
| SambaNova | DeepSeek V3.1, Llama 3.3 70B, gpt-oss-120b | 20 per minute, 20 per day, 200K tokens per day, per model | Docs say no, but the plans page now asks new users to add a card and buy credits |
| Cloudflare Workers AI | Open models incl. Llama, Qwen, gpt-oss | 10,000 neurons per day | No |
| NVIDIA (build.nvidia.com) | Many open models | "Free inference", limits not published | No |
| Z.ai | GLM-4.7-Flash, GLM-4.5-Flash, GLM-4.6V-Flash | Free, limits not published | No |
| Mistral | Mistral models in free mode | "Usage and rate limits apply", not published | No |
| Cerebras | gpt-oss-120b, Qwen 3.8 27B | Trial only: $5 credit, expires in 30 days | Yes |
No longer free, so skip them: GitHub Models (retired July 30, 2026), Hugging Face Inference Providers (free accounts get no monthly credit now; PRO gets $2), Ollama Cloud (the free plan is pay as you go, with no included credits), Together AI (minimum $5 purchase), Chutes (paid plans only), and Qwen Code's free login (ended April 15, 2026).
The cheap option: when free is not enough
If free limits keep stopping you, the next step is not a $20 subscription. It is a cheap API.
- DeepSeek is the value leader.
deepseek-flash(now DeepSeek V4.1 Flash) costs $0.15 to $0.30 per million input tokens and $0.60 to $1.20 per million output tokens, with off-peak at half price. A full day of agent work often costs well under a dollar. - opencode Go at $10 a month covers about 30 models with rolling allowances.
- Z.ai GLM-5.3 is $1.40 input and $4.40 output per million tokens, and one of the better open models for agent work.
Our recommended free setups
- Easiest: install opencode and use a free Zen model. Nothing else to sign up for.
- Most capable free: opencode or Cline with OpenRouter, after the one-time $10 top-up for 1,000 requests a day. Try several
:freemodels and keep the one that handles tool calls reliably. - Fastest: Groq's free plan with gpt-oss-120b. Very quick responses, and the most generous published daily cap.
- Keep Claude Code: route it through OpenRouter free models, as in our Claude Code free setup guide.
- Fully offline: a local model through Ollama. Free forever, private, but you need a strong GPU or Apple Silicon Mac for usable coding models. See how to self-host Gemma 4 for a starting point.
- Pick one agent (opencode or Cline)
- Create an OpenRouter account and API key
- Test two or three free models on a small real task
- Add an AGENTS.md so every model gets the same project rules
- Re-check limits monthly: they change without notice
Want to know how the paid agents compare? Read Claude Code vs Codex vs Gemini CLI vs opencode. For project rules that work across every agent, see our AGENTS.md and CLAUDE.md examples.
Is Gemini CLI still free?
What is the best free AI coding agent?
How many free requests does OpenRouter give?
Which free API has the highest limits for coding?
Is there a completely free Claude Code alternative?
Can I still use Claude models for free in Antigravity?
Sumit
ContributorHi, I'm Sumit, Being an introvert I have always been obsessed with technology-computers and reading dozens of posts to learn, find answers out of my curiosity. I love to write as I explore more.
