[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-75062":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":41,"readmeContent":42,"aiSummary":43,"trendingCount":16,"starSnapshotCount":16,"syncStatus":44,"lastSyncTime":45,"discoverSource":46},75062,"free-coding-models","vava-nessa\u002Ffree-coding-models","vava-nessa","Find, benchmark and install in CLI 170+ FREE coding LLM models across 15+ providers in real time","",null,"HTML",1983,221,15,13,0,85,119,226,255,105.04,"Other",false,"main",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40],"ai","deepseek","free","free-ai","freeai","gpt","gptoss","kimi","nim","nvidia","nvidia-nim","nvidia-nim-api","nvidia-nims","openclaw","opencode","2026-06-12 04:01:17","\u003Cp align=\"center\">\n  \u003Cimg src=\"logo.webp\" alt=\"free-coding-models logo\" width=\"328\">\n\u003C\u002Fp>\n\n\u003Ch1 align=\"center\">free-coding-models\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  \u003Cstrong>Find the fastest free coding model in seconds\u003C\u002Fstrong>\u003Cbr>\n  Track ~170 models across ~15 trusted free or free-limited AI providers in real time\u003Cbr>\u003Cbr>\n  \u003Cstrong>Install Free API endpoints to your favorite AI coding tools:\u003C\u002Fstrong>\u003Cbr>\n  OpenCode CLI \u002F Desktop \u002F WebUI, OpenClaw, Crush, Goose, Aider, Kilo CLI, Qwen Code, OpenHands, Amp, Hermes, Continue, Cline, Xcode, Pi, Rovo, Gemini and more...\u003Cbr>\u003Cbr>\n  \u003Cstrong>Use Kimi K2, DeepSeek V3, GPT-OSS, Qwen3, MiniMax M2, GLM, Llama 4, Gemma 4, Devstral and more — for free\u003C\u002Fstrong>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fv\u002Ffree-coding-models?color=3d6b00&label=npm&logo=npm\" alt=\"npm version\" width=\"200\">\u003Cbr>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnode\u002Fv\u002Ffree-coding-models?color=3d6b00&logo=node.js\" alt=\"node version\" width=\"200\">\u003Cbr>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fnpm\u002Fl\u002Ffree-coding-models?color=3d6b00\" alt=\"license\" width=\"200\">\u003Cbr>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fmodels-170+-3d6b00?logo=nvidia\" alt=\"models count\" width=\"200\">\u003Cbr>\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fproviders-16-1a56db\" alt=\"providers count\" width=\"200\">\n\u003C\u002Fp>\n\n```bash\nnpm install -g free-coding-models\nfree-coding-models\n```\n\n\u003Cp align=\"center\">\n  create a free account on one of the \u003Ca href=\"#-list-of-free-ai-providers\">providers\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"#-why-this-tool\">💡 Why\u003C\u002Fa> •\n  \u003Ca href=\"#-quick-start\">⚡ Quick Start\u003C\u002Fa> •\n  \u003Ca href=\"#-list-of-free-ai-providers\">🟢 Providers\u003C\u002Fa> •\n  \u003Ca href=\"#-usage\">🚀 Usage\u003C\u002Fa> •\n  \u003Ca href=\"#-tui-keys\">⌨️ TUI Keys\u003C\u002Fa> •\n  \u003Ca href=\"#-features\">✨ Features\u003C\u002Fa> •\n  \u003Ca href=\"#-contributing\">📋 Contributing\u003C\u002Fa> •\n  \u003Ca href=\"#️-model-licensing--commercial-use\">⚖️ Licensing\u003C\u002Fa> •\n  \u003Ca href=\"#-telemetry\">📊 Telemetry\u003C\u002Fa> •\n  \u003Ca href=\"#️-security--trust\">🛡️ Security\u003C\u002Fa> •\n  \u003Ca href=\"#-other-free-ai-resources\">🆓 Other Free AI Resources\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"demo.gif\" alt=\"free-coding-models demo\" width=\"100%\">\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fdiscord.gg\u002FZTNFHvvCkU\">\u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FDiscord-Join%20the%20community-5865F2?logo=discord&logoColor=white&style=for-the-badge\" alt=\"Join our Discord\">\u003C\u002Fa>\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Csub>Made with ❤️ and ☕ by \u003Ca href=\"https:\u002F\u002Fvanessadepraute.dev\">Vanessa Depraute\u003C\u002Fa> (aka \u003Ca href=\"https:\u002F\u002Fvavanessa.dev\">Vava-Nessa\u003C\u002Fa>)\u003C\u002Fsub>\n\u003C\u002Fp>\n\n---\n\n## 💡 Why this tool?\n\nThere are **~170 cataloged free or free-limited coding models** across ~15 vetted providers. Which one is fastest right now? Which one is actually stable versus just lucky on the last ping?\n\nThis 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\u002Fvariance** (30%), **spike rate** (20%), and **uptime** (20%). \n\nIt 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.\n\n---\n\n## ⚡ Quick Start\n\n### 🟢 List of Free AI Providers\n\nCreate a free account on one provider below to get started:\n\n**~170 coding models** across ~15 active providers, ranked by practical free-tier usefulness.\n\n| # | Provider | Models | Tier range | Free tier | Env var |\n|---|----------|--------|-----------|-----------|--------|\n| 1 | [NVIDIA NIM](https:\u002F\u002Fbuild.nvidia.com) | 42 | S+ → C | ~40 RPM (no credit card) | `NVIDIA_API_KEY` |\n| 2 | [Groq](https:\u002F\u002Fconsole.groq.com\u002Fkeys) | 8 | S → B | 30 RPM, 1K‑14.4K req\u002Fday (no credit card) | `GROQ_API_KEY` |\n| 3 | [Cerebras](https:\u002F\u002Fcloud.cerebras.ai) | 4 | S+ → B | 30 RPM, 1M tokens\u002Fday (no credit card) | `CEREBRAS_API_KEY` |\n| 4 | [Google AI Studio](https:\u002F\u002Faistudio.google.com\u002Fapikey) | 6 | S+ → A | Gemini free quotas vary by model\u002Fregion | `GOOGLE_API_KEY` |\n| 5 | [GitHub Models](https:\u002F\u002Fmodels.github.ai) | 15 | S+ → C | Quota depends on GitHub\u002FCopilot tier | `GITHUB_TOKEN` |\n| 6 | [Mistral La Plateforme](https:\u002F\u002Fconsole.mistral.ai\u002Fapi-keys) | 7 | S+ → A | Experiment plan, free evaluation tier | `MISTRAL_API_KEY` |\n| 7 | [Cloudflare Workers AI](https:\u002F\u002Fdash.cloudflare.com) | 15 | S+ → B | 10K neurons\u002Fday, 300 RPM (no credit card) | `CLOUDFLARE_API_TOKEN` + `CLOUDFLARE_ACCOUNT_ID` |\n| 8 | [OpenRouter](https:\u002F\u002Fopenrouter.ai\u002Fkeys) | 31 | S+ → C | 50 req\u002Fday free, 1K\u002Fday with $10 spend | `OPENROUTER_API_KEY` |\n| 9 | [SambaNova](https:\u002F\u002Fcloud.sambanova.ai\u002Fapis) | 6 | S+ → A- | Small developer quota, useful for light usage | `SAMBANOVA_API_KEY` |\n| 10 | [OVHcloud AI Endpoints](https:\u002F\u002Fendpoints.ai.cloud.ovh.net) | 10 | S → B | 2 req\u002Fmin\u002FIP free, 400 RPM with key | `OVH_AI_ENDPOINTS_ACCESS_TOKEN` |\n| 11 | [Codestral](https:\u002F\u002Fconsole.mistral.ai\u002Fapi-keys) | 1 | B+ | 30 RPM, 2K req\u002Fday | `MISTRAL_API_KEY` |\n| 12 | [ZAI](https:\u002F\u002Fz.ai) | 2 | S | Free Flash models only | `ZAI_API_KEY` |\n| 13 | [Scaleway](https:\u002F\u002Fconsole.scaleway.com\u002Fiam\u002Fapi-keys) | 10 | S+ → B | 1M free tokens | `SCALEWAY_API_KEY` |\n| 14 | [Alibaba DashScope](https:\u002F\u002Fmodelstudio.console.alibabacloud.com) | 9 | S+ → A | 1M free tokens\u002Fmodel, Singapore, 90 days | `DASHSCOPE_API_KEY` |\n| 15 | [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) | 6 | S+ → A | 1,000 req\u002Fday with personal Google account | CLI tool ♊ |\n| 16 | [OpenCode Zen](https:\u002F\u002Fopencode.ai\u002Fzen) | 8 | S+ → A | Free with OpenCode account | Zen models ✨ |\n\n> 💡 One key is enough. Add more at any time with **`P`** inside the TUI.\n\n> 🧹 Audit cleanup: `iFlow` was removed because it shut down on April 17, 2026. `Together AI`, `Perplexity API`, `DeepInfra`, `Replicate`, `Fireworks`, `Hyperbolic`, `Hugging Face`, `SiliconFlow`, `Chutes AI`, and `Rovo` were removed from the active free catalog because they are paid, trial-credit only, too tiny to be useful, unclear as a stable free API, or tool-specific rather than a generally usable free provider.\n\n---\n\n### Tier scale\n\n| Tier | SWE-bench | Best for |\n|------|-----------|----------|\n| **S+** | ≥ 70% | Complex refactors, real-world GitHub issues |\n| **S** | 60–70% | Most coding tasks, strong general use |\n| **A+\u002FA** | 40–60% | Solid alternatives, targeted programming |\n| **A-\u002FB+** | 30–40% | Smaller tasks, constrained infra |\n| **B\u002FC** | \u003C 30% | Code completion, edge\u002Fminimal setups |\n\n**① Install and run:**\n\n```bash\nnpm install -g free-coding-models\nfree-coding-models\n```\n\nOn first run, you'll be prompted to enter your API key(s). You can skip providers and add more later with **`P`**.\n\nUse ⚡️ Command Palette! with **Ctrl+P**.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FUSE_%E2%9A%A1%EF%B8%8F%20COMMAND%20PALETTE-CTRL%2BP-22c55e?style=for-the-badge\" alt=\"Use ⚡️ Command Palette with Ctrl+P\">\n\u003C\u002Fp>\n\n---\n\n## 🐳 Docker\n\nRun FCM without installing Node.js using the official Docker image:\n\n```bash\n# Quick start (daemon + web UI on port 19280)\ndocker run -p 19280:19280 ghcr.io\u002Fvava-nessa\u002Ffree-coding-models:latest\n\n# With an API key\ndocker run -p 19280:19280 -e OPENROUTER_API_KEY=your_key ghcr.io\u002Fvava-nessa\u002Ffree-coding-models:latest\n```\n\nAccess the web dashboard at `http:\u002F\u002Flocalhost:19280\u002F` and configure your coding tool to use `http:\u002F\u002Flocalhost:19280\u002Fv1` with model `fcm`.\n\n### Available Image Tags\n\n| Tag | Description |\n|-----|-------------|\n| `latest` | Most recent release |\n| `v{major}.{minor}.{patch}` | Specific version (e.g., `v0.3.70`) |\n| `v{major}.{minor}` | Minor version (e.g., `v0.3`) |\n| `v{major}` | Major version (e.g., `v0`) |\n\n### Environment Variables\n\n| Variable | Default | Description |\n|----------|---------|-------------|\n| `FCM_HOST` | `0.0.0.0` | Host to bind to (set `127.0.0.1` for localhost-only) |\n| `FCM_PORT` | `19280` | Port to listen on |\n| `FREE_CODING_MODELS_TELEMETRY` | `0` | Disable telemetry |\n\nProvider API keys (all optional):\n\n```bash\ndocker run -p 19280:19280 \\\n  -e NVIDIA_API_KEY=your_key \\\n  -e GROQ_API_KEY=your_key \\\n  -e OPENROUTER_API_KEY=your_key \\\n  ghcr.io\u002Fvava-nessa\u002Ffree-coding-models:latest\n```\n\n### Docker Compose\n\nCreate a `docker-compose.yml`:\n\n```yaml\nversion: '3.8'\nservices:\n  fcm:\n    image: ghcr.io\u002Fvava-nessa\u002Ffree-coding-models:latest\n    container_name: fcm\n    restart: unless-stopped\n    ports:\n      - \"19280:19280\"\n    environment:\n      FREE_CODING_MODELS_TELEMETRY: \"0\"\n      FCM_HOST: \"0.0.0.0\"\n      OPENROUTER_API_KEY: ${OPENROUTER_API_KEY:-}\n    volumes:\n      - fcm-data:\u002Fhome\u002Ffcm\nvolumes:\n  fcm-data:\n```\n\nRun with `docker-compose up -d`. API keys can be passed via a `.env` file or environment variables.\n\n### Troubleshooting\n\n**Container won't start:**\n- Check logs: `docker logs fcm`\n- Verify port 19280 is not in use: `docker ps | grep 19280`\n\n**Health check fails:**\n- Wait 30s for initial probe cycle\n- Verify API keys are valid: `docker exec fcm curl http:\u002F\u002Flocalhost:19280\u002Fhealth`\n\n**Cannot connect from host:**\n- Ensure `FCM_HOST=0.0.0.0` (default)\n- Check firewall allows localhost connections\n\n**Data persistence:**\n- Config is stored in Docker volume `fcm-data`\n- Recreate the volume with `docker-compose down -v` to reset\n\n---\n\nNeed 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.\n\n**② Pick a model and launch your tool:**\n\n```\n↑↓ navigate   →   Enter to launch\n```\n\nThe model you select is automatically written into your tool's config (📦 OpenCode, 🦞 OpenClaw, 💘 Crush, etc.) and the tool opens immediately. Done.\n\nIf the active CLI tool is missing, FCM now catches it before launch, offers a tiny Yes\u002FNo install prompt, installs the tool with its official global command, then resumes the same model launch automatically.\n\n> 💡 You can also run `free-coding-models --goose --tier S` to pre-filter to S-tier models for Goose before the TUI even opens.\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"demo2.gif\" alt=\"free-coding-models TUI demo\" width=\"100%\">\n\u003C\u002Fp>\n\n## 🚀 Usage\n\n### Common scenarios\n\n```bash\n# \"I want the local web dashboard\"\nfree-coding-models --daemon\n\n# \"I want one local endpoint that fails over between free models\"\nfree-coding-models --daemon-bg\nfree-coding-models --daemon-status\n\n# \"Start with an elite-focused preset, then adjust filters live\"\nfree-coding-models --premium\n\n# \"I want to script this — give me JSON\"\nfree-coding-models --tier S --json | jq -r '.[0].modelId'\n\n# \"I want to configure OpenClaw with Groq's fastest model\"\nfree-coding-models --openclaw --origin groq\n```\n\nWhen launching the daemon (with `--daemon`), the web dashboard and router API are served from the same port. Configure tools with:\n\n| Field | Value |\n|-------|-------|\n| Router Base URL | `http:\u002F\u002Flocalhost:19280\u002Fv1` |\n| Dashboard URL | `http:\u002F\u002Flocalhost:19280\u002F` |\n| Model | `fcm` |\n| API key | `fcm-local` |\n\n### Smart Model Router\n\nThe **FCM Router** is a local OpenAI-compatible daemon that keeps running after the TUI closes. Point your coding tool at one localhost endpoint and let FCM route each request to the best available model in your active set.\n\n```bash\n# Start the router in the background\nfree-coding-models --daemon-bg\n\n# Check the active port, set, model count, uptime, and request totals\nfree-coding-models --daemon-status\n\n# Stop it cleanly\nfree-coding-models --daemon-stop\n\n# Auto-discover and live-probe models into a named set\nfree-coding-models --sync-set\nfree-coding-models --sync-set my-coding-set\n```\n\nConfigure tools with:\n\n| Field | Value |\n|-------|-------|\n| Base URL | `http:\u002F\u002Flocalhost:19280\u002Fv1` |\n| Model | `fcm` |\n| API key | `fcm-local` |\n\nThe daemon auto-creates a `fast-coding` set from your configured providers on first start. It stores router settings in `~\u002F.free-coding-models.json`, writes lifecycle logs to `~\u002F.free-coding-models-daemon.log`, and tracks token metadata in `~\u002F.free-coding-models-tokens.json`.\n\nRouter endpoints:\n\n| Endpoint | Purpose |\n|----------|---------|\n| `POST \u002Fv1\u002Fchat\u002Fcompletions` | Route through the active set |\n| `POST \u002Fv1\u002Fsets\u002F:name\u002Fchat\u002Fcompletions` | Route through a named set |\n| `GET \u002Fv1\u002Fmodels` | Return virtual models (`fcm`, `fcm:set-name`) |\n| `GET \u002Fhealth` | Daemon status JSON |\n| `GET \u002Fstats` | Routing, health, request log, and token stats |\n| `GET \u002Fstream\u002Fevents` | Live SSE events for router updates |\n| `POST \u002Fdaemon\u002Fprobe-mode` | Set probe mode with `{ \"probeMode\": \"eco\" | \"balanced\" | \"aggressive\" }` |\n\n**Web Dashboard endpoints** (served from the same port in `--daemon` mode):\n\n| Endpoint | Purpose |\n|----------|---------|\n| `GET \u002F` | Web dashboard HTML |\n| `GET \u002Fapi\u002Fmodels` | All model data with latency stats |\n| `GET \u002Fapi\u002Fconfig` | Provider config (keys masked) |\n| `GET \u002Fapi\u002Fevents` | Live SSE events for dashboard |\n| `GET \u002Fapi\u002Fkey\u002F:provider` | Reveal full API key for provider |\n| `POST \u002Fapi\u002Fsettings` | Save API keys and provider toggles |\n\nRouting behavior:\n\n- Priority order works immediately on cold start, then probes refine health scores over time.\n- Transient failures (`429`, `500`, `502`, `503`, timeouts) fail over to the next model.\n- Authentication problems (`401`, `403`, missing keys) are marked separately so bad credentials do not poison the circuit breaker; after one provider returns an auth error, the router skips the rest of that provider for the current request.\n- Upstream HTML maintenance pages and malformed successful JSON are treated as retryable provider failures instead of being forwarded to your coding tool.\n- Quota and rate-limit failures include retry headers in the final router `503` payload when providers expose them.\n- If a coding tool disconnects mid-request, the daemon aborts the upstream request without counting it as a provider failure.\n- Streaming requests retry before the first byte; after partial output starts, the daemon records the failure and lets the current stream finish as safely as possible.\n\n### Tool launcher flags\n\n| Flag | Launches |\n|------|----------|\n| `--opencode` | 📦 OpenCode CLI |\n| `--opencode-desktop` | 📦 OpenCode Desktop |\n| `--opencode-web` | 📦 OpenCode WebUI |\n| `--openclaw` | 🦞 OpenClaw |\n| `--crush` | 💘 Crush |\n| `--goose` | 🪿 Goose |\n| `--aider` | 🛠 Aider |\n| `--kilo` | ⚡️ Kilo CLI |\n| `--qwen` | 🐉 Qwen Code |\n| `--openhands` | 🤲 OpenHands |\n| `--amp` | ⚡ Amp |\n| `--hermes` | 🔮 Hermes |\n| `--continue` | ▶️ Continue CLI |\n| `--cline` | 🧠 Cline |\n| `--xcode` | 🛠️ Xcode Intelligence |\n| `--pi` | π Pi |\n| `--rovo` | 🦘 Rovo Dev CLI |\n| `--gemini` | ♊ Gemini CLI |\n| `--copilot` | 🤖 Copilot CLI |\n| `--forgecode` | 🔥 ForgeCode |\n\nPress **`Z`** in the TUI to cycle between tools without restarting.\n\n### CLI-Only Tools\n\n**🦘 Rovo Dev CLI**\n- Provider: [Atlassian Rovo](https:\u002F\u002Fwww.atlassian.com\u002Frovo)\n- Install: [Installation Guide](https:\u002F\u002Fsupport.atlassian.com\u002Frovo\u002Fdocs\u002Finstall-and-run-rovo-dev-cli-on-your-device\u002F)\n- Free tier: conditional Atlassian\u002FRovo allowance, not a general free API provider\n- Catalog status: not included in the active free-provider table because access depends on Rovo availability for your account\u002Fsite\n- Launch: `free-coding-models --rovo` or press `Z` until Rovo mode\n- Features: Jira\u002FConfluence integration, MCP server support\n\n**♊ Gemini CLI**\n- Provider: [Google Gemini](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli)\n- Install: `npm install -g @google\u002Fgemini-cli`\n- Free tier: 1,000 requests\u002Fday (personal Google account, no credit card)\n- Models: Gemini 3.1 Pro Preview, Gemini 3 Flash Preview, Gemini 2.5 Pro, Gemini 2.5 Flash\n- Launch: `free-coding-models --gemini` or press `Z` until Gemini mode\n- Features: OpenAI-compatible API support, MCP server support, Google Search grounding\n\n**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.\n\n### OpenCode Zen Free Models\n\n[OpenCode Zen](https:\u002F\u002Fopencode.ai\u002Fzen) 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.\n\n| Model | Tier | SWE-bench | Context |\n|-------|------|-----------|---------|\n| Big Pickle | S+ | 72.0% | 200k |\n| MiniMax M2.5 Free | S+ | 80.2% | 200k |\n| Nemotron 3 Super Free | A+ | 52.0% | 1M |\n| GPT 5 Nano | S | 65.0% | 400k |\n| HY3 Preview Free | A+ | - | 128k |\n| Ling 2.6 Flash Free | S | - | 128k |\n| Trinity Large Preview Free | S | - | 128k |\n| Trinity Mini Preview Free | A | - | 128k |\n\nTo use Zen models: sign up at [opencode.ai\u002Fauth](https:\u002F\u002Fopencode.ai\u002Fauth) and enter your Zen API key via `P` (Settings). Zen models appear in the main table and auto-switch to OpenCode CLI on launch.\n\n### Tool Compatibility\n\nWhen 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.\n\n| Model Type | Compatible Tools |\n|------------|-----------------|\n| Regular (NVIDIA, Groq, etc.) | All tools except 🦘 Rovo and ♊ Gemini |\n| Rovo | 🦘 Rovo Dev CLI only |\n| Gemini | ♊ Gemini CLI only |\n| OpenCode Zen | 📦 OpenCode CLI and 📦 OpenCode Desktop only |\n\n→ **[Full flags reference](.\u002Fdocs\u002Fflags.md)**\n\n---\n\n## ⌨️ TUI Keys\n\n### Keyboard\n\n| Key | Action |\n|-----|--------|\n| `↑↓` | Navigate models |\n| `Enter` | Launch selected model in active tool |\n| `Z` | Cycle target tool |\n| `T` | Cycle tier filter |\n| `D` | Cycle provider filter |\n| `E` | Cycle visibility filter (`Active only → Configured only → Usable only`) |\n| `F` | Favorite \u002F unfavorite model |\n| `Y` | Toggle favorites mode (`Normal filter\u002Fsort` default ↔ `Pinned + always visible`) |\n| `X` | Clear active custom text filter |\n| `G` | Cycle global theme (`Auto → Dark → Light`) |\n| `Ctrl+P` | Open ⚡️ command palette (search + run actions) |\n| `R\u002FS\u002FC\u002FM\u002FO\u002FL\u002FA\u002FH\u002FV\u002FB\u002FU` | Sort columns |\n| `Shift+U` | Update to latest version (when update available) |\n| `P` | Settings (API keys, providers, updates, theme) |\n| `Q` | Smart Recommend overlay |\n| `N` | Changelog |\n| `W` | Cycle ping cadence |\n| `I` | Feedback \u002F bug report |\n| `K` | Help overlay |\n| `Ctrl+C` | Exit |\n\n### Mouse\n\n| Action | Result |\n|--------|--------|\n| **Click column header** | Sort by that column |\n| **Click Tier header** | Cycle tier filter |\n| **Click CLI Tools header** | Cycle tool mode |\n| **Click model row** | Move cursor to model |\n| **Double-click model row** | Select and launch model |\n| **Right-click model row** | Toggle favorite |\n| **Scroll wheel** | Navigate table \u002F overlays \u002F palette |\n| **Click footer hotkey** | Trigger that action |\n| **Click update banner** | Install latest version and relaunch |\n| **Click command palette item** | Select item (double-click to confirm) |\n| **Click recommend option** | Select option (double-click to confirm) |\n| **Click outside modal** | Close command palette |\n\n→ **[Stability score & column reference](.\u002Fdocs\u002Fstability.md)**\n\n---\n\n## ✨ Features\n\n- **Parallel pings** — all ~165 API\u002FZen-callable models tested simultaneously via native `fetch` (~170 total cataloged models including CLI-only Gemini rows)\n- **Adaptive monitoring** — 2s burst for 60s → 10s normal → 30s idle\n- **Stability score** — composite 0–100 (p95 latency, jitter, spike rate, uptime)\n- **Smart ranking** — top 3 highlighted 🥇🥈🥉\n- **Favorites** — star models with `F`, persisted across sessions, default to normal rows, and switch display mode with `Y` (pinned+sticky vs normal rows)\n- **Configured-only default** — only shows providers you have keys for\n- **Keyless latency** — models ping even without an API key (show 🔑 NO KEY)\n- **Smart Recommend** — questionnaire picks the best model for your task type\n- **Smart Model Router** — local OpenAI-compatible daemon with model sets, failover, circuit breakers, health probes, and token stats\n- **⚡️ Command Palette** — `Ctrl+P` opens a searchable action launcher for filters, sorting, overlays, and quick toggles\n- **Install Endpoints** — push a full provider catalog into any tool's config (from Settings `P` or ⚡️ Command Palette)\n- **Missing tool bootstrap** — detect absent CLIs, offer one-click install, then continue the selected launch automatically\n- **Tool compatibility matrix** — incompatible rows highlighted in dark red when a tool mode is active\n- **OpenCode Zen models** — 8 free models exclusive to OpenCode CLI\u002FDesktop, powered by the Zen AI gateway\n- **Width guardrail** — shows a warning instead of a broken table in narrow terminals\n- **Readable everywhere** — semantic theme palette keeps table rows, overlays, badges, and help screens legible in dark and light terminals\n- **Global theme switch** — `G` cycles `auto`, `dark`, + `light` live without restarting\n- **Auto-retry** — timeout models keep getting retried\n- **Aggressive update nudging** — fluorescent green banner when an update is available, impossible to miss, Shift+U hotkey, command palette entry, background re-check every 5 min, mid-session updates the banner live without restarting\n- **Last release timestamp** — light pink footer shows `Last release: Mar 27, 2026, 09:42 PM` from npm so users know how fresh the data is\n\n---\n\n## 📋 Contributing\n\nWe welcome contributions — issues, PRs, new provider integrations.\n\n**Q:** How accurate are the latency numbers?  \n**A:** Real round-trip times measured by your machine. Results depend on your network and provider load at that moment.\n\n**Q:** Can I add a new provider?  \n**A:** Yes — see [`sources.js`](.\u002Fsources.js) for the model catalog format.\n\n→ **[Development guide](.\u002Fdocs\u002Fdevelopment.md)** · **[Config reference](.\u002Fdocs\u002Fconfig.md)** · **[Tool integrations](.\u002Fdocs\u002Fintegrations.md)**\n\n---\n\n## ⚖️ Model Licensing & Commercial Use\n\n**Short answer:** The ~170 cataloged models are API\u002FCLI-served models where generated-output ownership is generally granted by the provider\u002Fmodel terms. Always verify current provider terms for high-stakes commercial use.\n\n### Output Ownership\n\nFor every model in this tool, **you own the generated output** — code, text, or otherwise — and can use it commercially. The licenses below govern the *model weights themselves*, not your generated content.\n\n### License Breakdown by Model Family\n\n| License | Models | Commercial Output |\n|---------|--------|:-----------------:|\n| **Apache 2.0** | Qwen3\u002FQwen3.5\u002FQwen2.5 Coder, GPT-OSS 120B\u002F20B, Devstral 2, Gemma 4 | ✅ Unrestricted |\n| **MIT \u002F permissive model terms** | GLM Flash, MiniMax M2.x, Devstral 2 | ✅ Provider\u002Fmodel terms apply |\n| **Modified MIT** | Kimi K2\u002FK2.6 (>100M MAU → display \"Kimi K2\" branding) | ✅ With attribution at scale |\n| **Llama Community License** | Llama 3.3 70B, Llama 4 Scout\u002FMaverick | ✅ Attribution required. >700M MAU → separate Meta license |\n| **DeepSeek License** | DeepSeek V3\u002FV3.1\u002FV3.2\u002FV4 family | ✅ Use restrictions on model (no military, no harm) — output is yours |\n| **NVIDIA Nemotron License** | Nemotron Super\u002FUltra\u002FNano | ✅ Updated Mar 2026, now near-Apache 2.0 permissive |\n| **MiniMax Model License** | MiniMax M2, M2.5 | ✅ Royalty-free, non-exclusive. Prohibited uses policy applies to model |\n| **Proprietary \u002F hosted API terms** | Gemini, GitHub Models, Mistral\u002FCodestral, OpenRouter-hosted models | ✅ Provider ToS applies |\n| **OpenCode Zen** | Big Pickle, GPT 5 Nano, MiniMax M2.5 Free, Nemotron 3 Super Free, HY3\u002FLing\u002FTrinity previews | ✅ Per OpenCode Zen ToS |\n\n### Key Points\n\n1. **Generated code is yours** — no model claims ownership of your output\n2. **Apache 2.0 \u002F permissive model families** (Qwen, GLM Flash, GPT-OSS, Devstral, Gemma) are the lowest-friction options\n3. **Llama** requires \"Built with Llama\" attribution; >700M MAU needs a Meta license\n4. **DeepSeek \u002F MiniMax** have use-restriction policies (no military use) that govern the model, not your generated code\n5. **API-served models** (Gemini, GitHub Models, OpenRouter, Mistral, etc.) grant output ownership under their current terms of service\n\n> ⚠️ **Disclaimer:** This is a summary, not legal advice. License terms can change. Always verify the current license on the model's official page before making legal decisions.\n\n---\n\n## 📊 Telemetry\n\n`free-coding-models` collects anonymous usage telemetry to help understand how the CLI is used and improve the product. No personal information, API keys, prompts, source code, file paths, or secrets are ever collected.\n\nThe telemetry payload is limited to anonymous product analytics such as the app version, selected tool mode, operating system, terminal family, and a random anonymous install ID stored locally on your machine. When a model is launched, telemetry can also include the selected tool, provider, model ID, model label, model tier, launch result, and a few product actions such as installing provider catalogs, saving\u002Fremoving API keys, or toggling shell environment export.\n\nTelemetry is enabled by default and can be disabled with any of the following:\n\n| Method | How |\n|--------|-----|\n| CLI flag | Run `free-coding-models --no-telemetry` |\n| Environment variable | Set `FREE_CODING_MODELS_TELEMETRY=0` (also supports `false` or `off`) |\n\n---\n\n## 🛡️ Security & Trust\n\n\u003Cp align=\"center\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fdependencies-1-76b900?logo=npm\" alt=\"1 dependency\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fprovenance-sigstore-blueviolet?logo=signstore\" alt=\"npm provenance\">\n  \u003Cimg src=\"https:\u002F\u002Fimg.shields.io\u002Fbadge\u002Fsupply_chain-verified-brightgreen\" alt=\"supply chain verified\">\n\u003C\u002Fp>\n\n### Supply Chain\n\n| Signal | Status |\n|--------|--------|\n| **npm Provenance** | ✅ Published with Sigstore-signed provenance |\n| **SBOM** | ✅ Software Bill of Materials attached to every GitHub Release |\n| **Dependencies** | ✅ 1 runtime dependency (`chalk`) |\n| **Lockfile** | ✅ `pnpm-lock.yaml` committed and tracked |\n| **Security Policy** | ✅ [`SECURITY.md`](SECURITY.md) |\n| **Code Owners** | ✅ [`CODEOWNERS`](CODEOWNERS) — all changes require maintainer review |\n| **Dependabot** | ✅ Weekly automated dependency + GitHub Actions updates |\n| **Audit CI** | ✅ `npm audit` runs on every push\u002FPR + weekly scheduled scan |\n| **License** | ✅ MIT |\n\n### What This Tool Does\n\n- Pings public API endpoints to measure latency and check availability\n- Reads your API keys from `.env` files (only if you configure them)\n- Opens configuration files for editing (with your permission)\n- Reports anonymous usage data (no personal information — see footer)\n\n### What This Tool Does NOT Do\n\n- ❌ Does **not** send your API keys, code, or personal data to any third party\n- ❌ Does **not** install or execute arbitrary code beyond `chalk` (the only dependency)\n- ❌ Does **not** modify any files outside its own config directory\n- ❌ Does **not** require `sudo`, root, or elevated permissions\n\n> To report a vulnerability, see [`SECURITY.md`](SECURITY.md).\n\n---\n\n## Star History\n\n\u003Ca href=\"https:\u002F\u002Fwww.star-history.com\u002F?repos=vava-nessa%2Ffree-coding-models&type=timeline&logscale=&legend=top-left\">\n \u003Cpicture>\n   \u003Csource media=\"(prefers-color-scheme: dark)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=vava-nessa\u002Ffree-coding-models&type=timeline&theme=dark&logscale&legend=top-left\" \u002F>\n   \u003Csource media=\"(prefers-color-scheme: light)\" srcset=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=vava-nessa\u002Ffree-coding-models&type=timeline&logscale&legend=top-left\" \u002F>\n   \u003Cimg alt=\"Star History Chart\" src=\"https:\u002F\u002Fapi.star-history.com\u002Fchart?repos=vava-nessa\u002Ffree-coding-models&type=timeline&logscale&legend=top-left\" \u002F>\n \u003C\u002Fpicture>\n\u003C\u002Fa>\n\n\n\n## Special thanks to contributors\n\n\u003Ctable align=\"center\">\n  \u003Ctr>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvava-nessa\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5466264?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"vava-nessa\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ferwinh22\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F6641858?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"erwinh22\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fwhit3rabbit\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12357518?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"whit3rabbit\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fskylaweber\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F172871734?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"skylaweber\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPhucTruong-ctrl\">\u003Cimg src=\"https:\u002F\u002Fgithub.com\u002FPhucTruong-ctrl.png?s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"PhucTruong-ctrl\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchindris-mihai-alexandru\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F12643176?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"chindris-mihai-alexandru\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fserajbaltu\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F90699173?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"serajbaltu\">\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\" width=\"120\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstgreenb\">\u003Cimg src=\"https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F18483964?v=4&s=80\" width=\"80\" height=\"80\" style=\"border-radius:50%\" alt=\"stgreenb\">\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n  \u003Ctr>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fvava-nessa\">\u003Csub>\u003Cb>vava-nessa\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Ferwinh22\">\u003Csub>\u003Cb>erwinh22\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fwhit3rabbit\">\u003Csub>\u003Cb>whit3rabbit\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fskylaweber\">\u003Csub>\u003Cb>skylaweber\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002FPhucTruong-ctrl\">\u003Csub>\u003Cb>PhucTruong-ctrl\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fchindris-mihai-alexandru\">\u003Csub>\u003Cb>chindris-mihai-alexandru\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fserajbaltu\">\u003Csub>\u003Cb>serajbaltu\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n    \u003Ctd align=\"center\">\u003Ca href=\"https:\u002F\u002Fgithub.com\u002Fstgreenb\">\u003Csub>\u003Cb>stgreenb\u003C\u002Fb>\u003C\u002Fsub>\u003C\u002Fa>\u003C\u002Ftd>\n  \u003C\u002Ftr>\n\u003C\u002Ftable>\n\n---\n\n## 🆓 Other Free AI Resources\n\n**Curated resources outside the active CLI catalog** — IDE extensions, coding agents, GitHub lists, and providers that are useful but not clean enough for the core free-provider table.\n\n### 📚 Awesome Lists (curated by the community)\n\n| Resource | What it is |\n|----------|------------|\n| [cheahjs\u002Ffree-llm-api-resources](https:\u002F\u002Fgithub.com\u002Fcheahjs\u002Ffree-llm-api-resources) (18.4k ⭐) | Comprehensive list of free LLM API providers with rate limits |\n| [mnfst\u002Fawesome-free-llm-apis](https:\u002F\u002Fgithub.com\u002Fmnfst\u002Fawesome-free-llm-apis) (2.1k ⭐) | Permanent free LLM API tiers organized by provider |\n| [inmve\u002Ffree-ai-coding](https:\u002F\u002Fgithub.com\u002Finmve\u002Ffree-ai-coding) (648 ⭐) | Pro-grade AI coding tools side-by-side — limits, models, CC requirements |\n| [amardeeplakshkar\u002Fawesome-free-llm-apis](https:\u002F\u002Fgithub.com\u002Famardeeplakshkar\u002Fawesome-free-llm-apis) | Additional free LLM API resources |\n\n### 🖥️ AI-Powered IDEs with Free Tiers\n\n| IDE | Free tier | Credit card |\n|-----|-----------|-------------|\n| [Qwen Code](https:\u002F\u002Fgithub.com\u002FQwenLM\u002Fqwen-code) | 2,000 requests\u002Fday | No |\n| [Rovo Dev CLI](https:\u002F\u002Fwww.atlassian.com\u002Frovo) | Conditional Atlassian\u002FRovo allowance | No |\n| [Gemini CLI](https:\u002F\u002Fgithub.com\u002Fgoogle-gemini\u002Fgemini-cli) | 1,000 requests\u002Fday | No |\n| [Jules](https:\u002F\u002Fjules.google\u002F) | 15 tasks\u002Fday | No |\n| [AWS Kiro](https:\u002F\u002Fkiro.dev\u002F) | 50 credits\u002Fmonth | No |\n| [Trae](https:\u002F\u002Ftrae.ai\u002F) | 10 fast + 50 slow requests\u002Fmonth | No |\n| [Codeium](https:\u002F\u002Fcodeium.com\u002F) | Unlimited forever, basic models | No |\n| [JetBrains AI Assistant](https:\u002F\u002Fwww.jetbrains.com\u002Fai\u002F) | Unlimited completions + local models | No |\n| [Continue.dev](https:\u002F\u002Fwww.continue.dev\u002F) | Free VS Code\u002FJetBrains extension, local models via Ollama | No |\n| [Warp](https:\u002F\u002Fwarp.dev\u002F) | 150 credits\u002Fmonth (first 2 months), then 75\u002Fmonth | No |\n| [Amazon Q Developer](https:\u002F\u002Faws.amazon.com\u002Fq\u002Fdeveloper\u002F) | 50 agentic requests\u002Fmonth | Required |\n| [Windsurf](https:\u002F\u002Fwindsurf.com\u002F) | 25 prompt credits\u002Fmonth | Required |\n| [Kilo Code](https:\u002F\u002Fkilocode.ai\u002F) | Up to $25 signup credits (one-time) | Required |\n| [Tabnine](https:\u002F\u002Fwww.tabnine.com\u002F) | Basic completions + chat (limited) | Required |\n| [SuperMaven](https:\u002F\u002Fsupermaven.com\u002F) | Basic suggestions, 1M token context | Required |\n\n### 🔑 API Providers with Permanent Free Tiers\n\n| Provider | Free limits | Notable models |\n|----------|-------------|----------------|\n| [OpenRouter](https:\u002F\u002Fopenrouter.ai\u002Fkeys) | 50 req\u002Fday, 1K\u002Fday with $10 purchase | Qwen3-Coder, Tencent HY3, Laguna, Gemma 4 |\n| [Google AI Studio](https:\u002F\u002Faistudio.google.com\u002Fapikey) | Varies by Gemini model and region | Gemini 3.1 Pro Preview, Gemini 2.5 Flash |\n| [NVIDIA NIM](https:\u002F\u002Fbuild.nvidia.com) | ~40 RPM | MiniMax M2.7, GLM 5.1, Kimi K2.6 |\n| [GitHub Models](https:\u002F\u002Fmodels.github.ai) | Depends on GitHub\u002FCopilot tier | GPT-4.1, DeepSeek V3, Llama 4 |\n| [Groq](https:\u002F\u002Fconsole.groq.com\u002Fkeys) | 1K–14.4K req\u002Fday (model-dependent) | Llama 3.3 70B, Llama 4 Scout, GPT-OSS |\n| [Cerebras](https:\u002F\u002Fcloud.cerebras.ai\u002F) | 30 RPM, 1M tokens\u002Fday | Qwen3-235B, Llama 3.1 70B, GPT-OSS 120B |\n| [Cohere](https:\u002F\u002Fcohere.com\u002F) | 20 RPM, 1K\u002Fmonth | Command R+, Aya Expanse 32B |\n| [Mistral La Plateforme](https:\u002F\u002Fconsole.mistral.ai\u002F) | 1 req\u002Fs, 1B tokens\u002Fmonth | Mistral Large, Devstral, Magistral |\n| [Cloudflare Workers AI](https:\u002F\u002Fdash.cloudflare.com) | 10K neurons\u002Fday | Llama 3.3 70B, QwQ 32B, 47+ models |\n| [OVHcloud AI Endpoints](https:\u002F\u002Fendpoints.ai.cloud.ovh.net) | 2 req\u002Fmin\u002FIP sandbox | GPT-OSS, Qwen3, Mistral |\n\n### 🧪 Good Candidates Kept Outside the Core Catalog\n\n| Provider | Why it is not core |\n|----------|--------------------|\n| [Vercel AI Gateway](https:\u002F\u002Fvercel.com\u002Fdocs\u002Fai-gateway) | Useful gateway with included credits, but it is a router\u002Fbilling layer, not a provider of permanently free models. |\n| [Cohere](https:\u002F\u002Fcohere.com\u002F) | Real evaluation key, but the allowance is small and the catalog is not coding-first enough for the default TUI. |\n| [Ollama Cloud](https:\u002F\u002Follama.com\u002Fpricing) | Interesting for light cloud usage, but it is closer to hosted Ollama capacity than a classic OpenAI-compatible free provider. |\n\n### 💰 Providers with Trial Credits\n\n| Provider | Credits | Duration |\n|----------|---------|----------|\n| [Hyperbolic](https:\u002F\u002Fapp.hyperbolic.ai\u002F) | $1 | Trial\u002Fpromo |\n| [Fireworks](https:\u002F\u002Ffireworks.ai\u002F) | $1 | Trial\u002Fpromo |\n| [Nebius](https:\u002F\u002Ftokenfactory.nebius.com\u002F) | $1 | Permanent |\n| [SambaNova Cloud](https:\u002F\u002Fcloud.sambanova.ai\u002F) | $5 | 3 months |\n| [AI21](https:\u002F\u002Fstudio.ai21.com\u002F) | $10 | 3 months |\n| [Upstage](https:\u002F\u002Fconsole.upstage.ai\u002F) | $10 | 3 months |\n| [NLP Cloud](https:\u002F\u002Fnlpcloud.com\u002Fhome) | $15 | Permanent |\n| [Alibaba DashScope](https:\u002F\u002Fbailian.console.alibabacloud.com\u002F) | 1M tokens\u002Fmodel | 90 days |\n| [Scaleway](https:\u002F\u002Fconsole.scaleway.com\u002Fgenerative-api\u002Fmodels) | 1M tokens | Permanent |\n| [Modal](https:\u002F\u002Fmodal.com) | $5\u002Fmonth | Monthly |\n| [Inference.net](https:\u002F\u002Finference.net) | $1 (+ $25 on survey) | Permanent |\n| [Novita](https:\u002F\u002Fnovita.ai\u002F) | $0.5 | 1 year |\n\nThese trial-credit providers are deliberately not treated as core providers unless their free allowance is practical for recurring coding use. A $0.10\u002Fmonth or $1 one-time credit is useful for experimentation, not for this CLI's default promise.\n\n### 🎓 Free with Education\u002FDeveloper Programs\n\n| Program | What you get |\n|---------|--------------|\n| [GitHub Student Pack](https:\u002F\u002Feducation.github.com\u002Fpack) | Free Copilot Pro for students (verify with .edu email) |\n| [GitHub Copilot Free](https:\u002F\u002Fcode.visualstudio.com\u002Fblogs\u002F2024\u002F12\u002F18\u002Ffree-github-copilot) | 50 chat + 2,000 completions\u002Fmonth in VS Code |\n| [Copilot Pro for teachers\u002Fmaintainers](https:\u002F\u002Fdocs.github.com\u002Fen\u002Fcopilot\u002Fhow-tos\u002Fmanage-your-account\u002Fget-free-access-to-copilot-pro) | Free Copilot Pro for open source maintainers & educators |\n","free-coding-models 是一个用于发现、基准测试并安装超过170个免费编码大模型的命令行工具，这些模型来自15个以上的提供商。该项目的核心功能包括实时追踪和比较各大模型的性能，提供了一个稳定性评分（0-100），该评分基于p95延迟等指标计算得出，从而帮助用户识别最快速且稳定的模型。此外，它还支持将选定的API端点直接集成到多种流行的AI编码工具中，如OpenCode CLI、Kilo CLI、Qwen Code等。此工具非常适合需要高效找到最佳免费编程助手的开发者使用。",2,"2026-06-11 03:52:09","high_star"]