Independent open-source project. Not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.
What You Get
- 61 ToS-friendly providers. 1.3B+ free tokens every month. Use free, paid, subscription, and local models from one searchable UI without putting your account at risk. FCC follows provider terms and removes integrations if they stop being allowed.
- 11 coding agents. One model catalog. Run Claude Code, Codex, Pi, OpenCode, Cline, Hermes, DeepSeek Harness, Grok Build, Muse Code, Aider, or VS Code Chat with your FCC models.
- Keep coding through provider outages. After retries are exhausted, FCC automatically tries your next configured model without making you restart the turn. This works across every client.
- Up to 90% lower token usage. Optional RTK filters common command output, and Headroom compresses tool results. Five FCC optimizations handle quota probes, command-prefix detection, titles, suggestions, and filepaths without calling a provider.
- Native Code sessions in your browser. Choose a folder and run Codex in the browser with real-time and background support. Freely switch providers/models in the same session. Support for switching harnesses in the same session coming soon!
- Terminal, desktop, IDE, or phone. Work through native launchers, VS Code, Codex App, JetBrains, Discord, or Telegram.
- Voice notes in. Code out. Talk to your agent using local Whisper or NVIDIA NIM transcription.
- Agent capabilities stay intact. Stream responses, use tools, preserve native interleaved thinking for maximum performance, send images, and route Fable, Opus, Sonnet, and Haiku independently with compatible models.
Free-tier availability and limits are controlled by each provider and may change.
Claude Code running with FCC.
A native Codex session in FCC's browser UI.
Quick Start
1. Install
macOS/Linux:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | shWindows PowerShell:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1")))When prompted, choose at least one coding agent and optionally enable RTK + Headroom token optimization for supported agents. You can review the installers before running them: install.sh and install.ps1.
2. Start FCC
Windows
Open Free Claude Code from your desktop or Start menu.
macOS
Open Free Claude Code from your desktop or Applications folder.
Linux
Run:
fcc-serverFCC opens the Admin UI after starting. On Windows and macOS, use the tray or
menu-bar icon to open Admin, restart, or quit. When using fcc-server, keep its
terminal open.
3. Configure NVIDIA NIM
- Create an API key at build.nvidia.com/settings/api-keys.
- Open the Admin UI URL from the server log.
- Paste the key into
NVIDIA_NIM_API_KEY. - Leave
MODELon the defaultnvidia_nim/nvidia/nemotron-3-super-120b-a12b, or search the model dropdown and select another model. - Click Apply.
To protect the local proxy with a bearer token, enable Proxy Authentication in Admin.
4. Run Your Coding Agent
Claude Code:
fcc-claudeCodex:
fcc-codexPi:
fcc-piOpenCode 2:
fcc-opencodeCline:
fcc-clineHermes:
fcc-hermesDeepSeek Harness Web:
fcc-dshGrok Build:
fcc-grokMuse Code:
fcc-museAider:
fcc-aider
Select an FCC model from Claude Code's native /model picker.
Choose A Provider
- Open a provider link below for its key, models, or setup instructions.
- In the Admin UI, configure the listed setting. For OpenAI / ChatGPT subscription access, use Providers → OAuth providers instead.
- Search the
MODELdropdown and select a model. If the provider cannot list models, enter<provider-id>/<exact-provider-model-id>manually. - Click Apply.
Optional: add an ordered Fallback Models list under Model Config. It applies to every connected client. A failed request may reach and consume usage from more than one provider before succeeding.
For another API endpoint, open Providers → Custom providers → Add provider. Enter its API base URL, optional key, and API format. Leave Model IDs empty to discover models automatically, or enter one upstream model ID per line. Save, then select a model in Model Config.
Provider catalog
| Provider | Admin UI setting | Example MODEL |
|---|---|---|
| NVIDIA NIM | NVIDIA_NIM_API_KEY | nvidia_nim/nvidia/nemotron-3-super-120b-a12b |
| OpenRouter | OPENROUTER_API_KEY | open_router/openrouter/free |
| Groq | GROQ_API_KEY | groq/llama-3.3-70b-versatile |
| ClinePass | CLINE_API_KEY | cline_pass/cline-pass/kimi-k3 |
| OpenAI / ChatGPT | Connect ChatGPT in the Admin UI | openai/<model-id> |
| OpenAI API | OPENAI_API_KEY | openai_api/gpt-5.6-sol |
| GitHub Copilot | Connect GitHub Copilot in the Admin UI | github_copilot/<model-id> |
| xAI (Grok) | XAI_API_KEY | xai/grok-4.5 |
| Alibaba Cloud | ALIBABA_CLOUD_API_KEY | alibaba_cloud/<model-id> |
| QwenCloud Token Plan | QWENCLOUD_API_KEY | qwencloud/qwen3.7-plus |
| QwenCloud Coding Plan | QWENCLOUD_CODING_API_KEY | qwencloud_coding/qwen3.7-plus |
| Together AI | TOGETHER_API_KEY | together/zai-org/GLM-5.2 |
| DeepInfra | DEEPINFRA_API_KEY | deepinfra/deepseek-ai/DeepSeek-V4-Flash |
| SiliconFlow | SILICONFLOW_API_KEY | siliconflow/Qwen/Qwen3-32B |
| Nebius Token Factory | NEBIUS_API_KEY | nebius/Qwen/Qwen3-30B-A3B |
| Chutes | CHUTES_API_KEY | chutes/Qwen/Qwen3-32B-TEE |
| Featherless AI | FEATHERLESS_API_KEY | featherless/Qwen/Qwen3-32B |
| Agnes AI | AGNES_API_KEY | agnes/agnes-2.0-flash |
| ZenMux | ZENMUX_API_KEY | zenmux/deepseek/deepseek-v4-flash-free |
| W&B Inference | WANDB_API_KEY | wandb/openai/gpt-oss-20b |
| Anthropic | ANTHROPIC_API_KEY | anthropic/<model-id> |
| Azure OpenAI | AZURE_OPENAI_API_KEY and AZURE_OPENAI_BASE_URL | azure_openai/<deployment-name> |
| Google AI Studio (Gemini) | GEMINI_API_KEY | gemini/models/gemini-3.1-flash-lite |
| Google Vertex AI | VERTEX_PROJECT_ID + ADC | vertex/google/gemini-3.5-flash |
| DeepSeek | DEEPSEEK_API_KEY | deepseek/deepseek-chat |
| Mistral La Plateforme | MISTRAL_API_KEY | mistral/devstral-small-latest |
| Mistral Codestral | CODESTRAL_API_KEY | mistral_codestral/codestral-latest |
| OpenCode Zen | OPENCODE_API_KEY | opencode_zen/gpt-5.3-codex |
| OpenCode Go | OPENCODE_API_KEY | opencode_go/minimax-m2.7 |
| Vercel AI Gateway | AI_GATEWAY_API_KEY | vercel/openai/gpt-5.5 |
| Amazon Bedrock | AWS_BEARER_TOKEN_BEDROCK | bedrock/openai.gpt-oss-120b |
| Hugging Face Inference Providers | HUGGINGFACE_API_KEY | huggingface/Qwen/Qwen3-Coder-480B-A35B-Instruct:fastest |
| Cohere | COHERE_API_KEY | cohere/command-a-plus-05-2026 |
| Wafer | WAFER_API_KEY | wafer/DeepSeek-V4-Pro |
| Kimi API | KIMI_API_KEY | kimi/kimi-k2.5 |
| Kimi Code | KIMI_CODE_API_KEY | kimi_code/k3 |
| MiniMax | MINIMAX_API_KEY | minimax/MiniMax-M3 |
| Cerebras Inference | CEREBRAS_API_KEY | cerebras/gpt-oss-120b |
| SambaNova | SAMBANOVA_API_KEY | sambanova/Meta-Llama-3.3-70B-Instruct |
| Kilo.ai | KILO_API_KEY | kilo/kilo-auto/free |
| Fireworks AI | FIREWORKS_API_KEY | fireworks/accounts/fireworks/models/llama-v3p3-70b-instruct |
| Novita AI | NOVITA_API_KEY | novita/deepseek/deepseek-v4-flash-0731 |
| Cloudflare Workers AI | CLOUDFLARE_API_TOKEN and CLOUDFLARE_ACCOUNT_ID | cloudflare/@cf/moonshotai/kimi-k2.6 |
| Z.ai Coding Plan | ZAI_API_KEY | zai/glm-5.2 |
| Z.ai API (pay as you go) | ZAI_API_KEY | zai_api/glm-4.7-flash |
| TokenRouter | TOKENROUTER_API_KEY | tokenrouter/moonshotai/kimi-k3-free |
| NaraRoute | NARAROUTE_API_KEY | nararoute/kimi-k3-free |
| Poolside AI | POOLSIDE_API_KEY | poolside/poolside/laguna-s-2.1 |
| LLM7.io | LLM7_API_KEY | llm7/default |
| Scaleway | SCW_SECRET_KEY | scaleway/deepseek/deepseek-v4-flash |
| Lightning AI | LIGHTNING_API_KEY | lightning/lightning-ai/Qwen3.8-27B |
| Experiential Labs | EXPLABS_API_KEY | experiential/union-alpha |
| Cheaper Inference | CHEAPER_INFERENCE_API_KEY | cheaperinference/gpt-5.4-mini |
| OrcaRouter | ORCAROUTER_API_KEY | orcarouter/deepseek/deepseek-v4-flash-free |
| Atlas Cloud | ATLASCLOUD_API_KEY | atlascloud/deepseek-ai/deepseek-v4-flash |
| xKiro | XKIRO_API_KEY | xkiro/qwen/qwen3.7-flash:free |
| Opper | OPPER_API_KEY | opper/claude-sonnet-4-6 |
| Ollama Cloud | OLLAMA_API_KEY | ollama_cloud/qwen3-coder:480b |
| LM Studio | LM_STUDIO_BASE_URL | lmstudio/<model-id> |
| llama.cpp | LLAMACPP_BASE_URL | llamacpp/<model-id> |
| Ollama | OLLAMA_BASE_URL | ollama/<model-tag> |
Provider-specific setup
- OpenAI / ChatGPT uses your ChatGPT subscription rather than an API key. Connect from Providers → OAuth providers → OpenAI / ChatGPT → Connect in the Admin UI and finish signing in through your browser. Restart an already-running agent after connecting.
- Anthropic uses a separately billed API key. Add it under
Providers → Cloud providers → Anthropic → Configure, then choose a discovered
model. Multi-workspace keys also require
ANTHROPIC_WORKSPACE_ID. Messages requests use Anthropic's native tools and the client's thinking controls. FCC local web tools and prompt optimizations apply to other routes. Native requests can fall back only to other Anthropic models. Anthropic tool access and charges apply. - OpenAI API uses a separate Platform API key. Enter it under Providers → Cloud providers → OpenAI API → Configure. The model list may include IDs that cannot handle coding requests. Choose a text-generation model.
- GitHub Copilot uses your signed-in GitHub account and subscription. Install
Copilot CLI 1.0.83
on PATH, then choose Providers → OAuth providers → GitHub Copilot → Connect.
Finish signing in, then select a
github_copilot/<model-id>from the model picker. Available models and quotas depend on your subscription and organization policies. Restart an already-running agent after connecting. - Azure OpenAI uses the deployment names from your resource. Set
AZURE_OPENAI_BASE_URLto its complete v1 endpoint, such ashttps://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/, and select a deployment that supports Chat Completions. Enter the deployment name as a custom model slug if it does not appear in the model dropdown. - Mistral Codestral uses a separate key from Mistral La Plateforme.
- Kimi Code subscription keys use
kimi_code/. Kimi API credit keys usekimi/. Kimi Code plans are for personal interactive coding-agent use under Kimi's community guidelines. - Alibaba Cloud uses a Model Studio pay-as-you-go key and defaults to Singapore.
For another region or workspace, set
ALIBABA_CLOUD_BASE_URLto its OpenAI-compatible endpoint ending in/compatible-mode/v1. The key and endpoint must use the same region. - QwenCloud Coding Plan keys use
qwencloud_coding/. QwenCloud Token Plan keys useqwencloud/. The keys and endpoints are not interchangeable. Coding Plan is for local, personal, interactive coding-agent use under the Coding Plan terms. - OpenCode Zen and OpenCode Go share
OPENCODE_API_KEYbut use the explicitopencode_zen/andopencode_go/model prefixes. - For Amazon Bedrock, set
BEDROCK_BASE_URLto the URL for the same region as the API key and select one of the listed models. - Vertex AI uses Google Application Default Credentials instead of an API key.
Locally, run
gcloud auth application-default loginonce. Service-account files and attached service accounts also work. SetVERTEX_PROJECT_ID, and optionally changeVERTEX_LOCATIONfrom itsglobaldefault. - Cloudflare requires both its API token and account ID.
- For Ollama Cloud, use the exact model IDs shown in the model picker. Local
Ollama uses the separate
ollama/prefix. - Prefer tool-capable models for coding agents. Local models also need enough context for the agent's system prompt and tool definitions.
Local provider setup
LM Studio
Start LM Studio's local server, load a tool-capable model, and use the model identifier shown by LM Studio with the lmstudio/ prefix. The default URL is http://localhost:1234/v1.
llama.cpp
Start llama-server with its OpenAI-compatible Chat Completions API and enough context for the model. Use the local model ID with the llamacpp/ prefix. LLAMACPP_BASE_URL defaults to http://localhost:8080/v1.
Ollama
ollama pull llama3.1
ollama serveUse the tag shown by ollama list with the ollama/ prefix. OLLAMA_BASE_URL defaults to http://localhost:11434.
Optional model-tier routing
MODEL is the fallback for every request. Select a model for MODEL_FABLE, MODEL_OPUS, MODEL_SONNET, or MODEL_HAIKU to override an individual Claude Code tier. Select None to use MODEL.
In Admin UI → Model Config, add Fallback Models in the order FCC should try them if the selected model fails. Each fallback has its own reasoning effort: Inherit, Off, From client, Low, Medium, High, X-High, or Max.
Choose a model and effort in the bottom row, then click +. Edit either dropdown in place, drag the handle to change the order, or click the red trash button to remove a fallback.
Inherit keeps the original request's resolved reasoning setting. From client uses the effort or token budget sent by your coding agent, bypassing the global or tier setting. A fallback matching the selected provider/model is skipped.
Reasoning control
Open Admin UI → Model Config → Model Routing and choose an effort beside each model. Default Effort starts at From client. Fable, Opus, Sonnet, and Haiku start at Inherit.
| Selection | Behavior |
|---|---|
| From client | Use the effort sent by your coding agent. If none is sent, keep the provider default. |
| Off | Request reasoning to be disabled. |
| Low, Medium, High, X-High, or Max | Override the client with the selected reasoning level. |
| Inherit | Tier overrides use Default Effort. Fallbacks keep the original request's resolved effort. |
Providers that do not support a selected control retain their own behavior.
Connect Your Client
For editor and app integrations, install the client, start FCC, then open Admin UI → Integrations and click Connect on its card.
- Claude Code in VS Code: Install the Claude Code extension.
- VS Code Chat: Install the latest VS Code, connect, and select an FCC model in its built-in Chat model picker.
- Claude Desktop: Install Claude Desktop. Fully quit it before connecting or disconnecting, then reopen it. Disconnect returns to normal Claude sign-in.
- Codex in VS Code and App: Install the Codex extension or Codex App.
- DeepSeek Harness Desktop: Install and open the app once before connecting. Start a new session to use FCC models.
- Claude Code in JetBrains ACP: Install Claude Agent in JetBrains AI Assistant and start it once, then click Connect in FCC. Reopen the IDE, select Claude Code (FCC), and start a new chat. After JetBrains updates the agent, restart FCC before starting a new chat. Requires a local IDE in its standard installation locations.
Reload VS Code or restart the app/IDE after connecting. In Codex and Claude Desktop, select an FCC model from the model picker. Reload or restart the client when FCC reports updated settings. Use Disconnect on the same card to remove the integration.
To complete Claude Code onboarding separately, open Admin UI → Integrations → Claude Code onboarding and click Complete onboarding. Connecting Claude Code in VS Code also completes onboarding.
Run FCC on the same computer and in the same user environment as the client you are configuring.
Optional Integrations
Configure integrations from Admin UI → Messaging, then click Apply.
Discord bot
- Create a bot in the Discord Developer Portal.
- Enable Message Content Intent and invite it with read, send,
message-history, and Manage Messages permissions so
/clearcan remove user prompts. - Set Messaging Platform to discord.
- Enter Discord Bot Token, Allowed Discord Channels, and an absolute Allowed Directory.
- Apply the settings and restart the server if requested.
Telegram bot
- Create a bot with @BotFather.
- Get your numeric user ID from @userinfobot. In groups, grant the bot permission to delete messages.
- Set Messaging Platform to telegram.
- Enter Telegram Bot Token, Allowed Telegram User ID, and an absolute Allowed Directory.
- Apply the settings and restart the server if requested.
Messaging commands
| Usage | Behavior |
|---|---|
/stats | Show session state. |
Standalone /stop | Cancel all work. |
Reply with /stop | Cancel only the selected request while other queued requests continue. |
Standalone /clear | Clear all FCC conversations and their messages in this chat. |
Reply with /clear | Delete the selected message and the chain of replies to it. Keep other conversations. |
Voice notes
NVIDIA NIM transcription support is included in every installation. In Admin UI → Messaging → Voice, enable voice notes, select nvidia_nim, and choose a supported model. Configure your NVIDIA NIM API key on the Providers page.
For local Whisper on CPU or CUDA, re-run the installer with the local voice option:
macOS/Linux:
Local Whisper on CPU or CUDA:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-localLocal Whisper with CUDA 13.0:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh -s -- --voice-local --torch-backend cu130Windows PowerShell:
Local Whisper on CPU or CUDA:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocalLocal Whisper with CUDA 13.0:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.ps1"))) -VoiceLocal -TorchBackend cu130After installing local support, restart fcc-server. In Admin UI → Messaging → Voice, enable voice notes, select cpu or cuda, and choose the Whisper model. Local gated models need HUGGINGFACE_API_KEY.
Manage Your Installation
Run fcc-server --version to check the installed version without starting FCC.
Update
Stop all running FCC commands, then run:
fcc-updateIf FCC is already up to date, the command stops without running the installer. Otherwise, it shows the installed and available versions before updating. If the version check fails, retry the command.
To reinstall FCC or change optional components while already up to date, run the installer directly.
For local voice support, include --voice-local (macOS/Linux) or -VoiceLocal (Windows), plus your --torch-backend or -TorchBackend option if used.
If your installation does not have fcc-update yet, run the installer once to add it.
Muse Code on native Windows
To install or update only Muse Code:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install-muse.ps1")))To remove the Muse Code copy installed by FCC, keeping its data:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall-muse.ps1")))Uninstalling FCC leaves Muse Code installed.
Uninstall
Stop every running FCC command before uninstalling.
Removes
- Free Claude Code, including its desktop launcher and commands
~/.fcc/
Keeps
- uv and Python
- Your coding agents, RTK, and Headroom
macOS/Linux:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall.sh" | shWindows PowerShell:
& ([scriptblock]::Create((irm "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/uninstall.ps1")))Project Links
For a problem after installation, run the command below and paste its output into your bug report. It also copies the JSON to your clipboard when available.
fcc-doctorLicense
GNU Affero General Public License version 3 only (AGPL-3.0-only). See LICENSE for details.