Use Claude Code, Codex, Pi, and OpenCode for free (1.3B+ free tokens) from your terminal, app, IDE, or phone like OpenClaw (voice supported + ToS friendly)
</div>
<p align="center">
<em>Independent open-source project. Not affiliated with or endorsed by Anthropic. Claude and Claude Code are trademarks of Anthropic.</em>
</p>
<div align="center">
<img src="assets/pic.png" alt="Claude Code running with Free Claude Code" width="700">
<p><em>Claude Code running with FCC.</em></p>
</div>
<div align="center">
<img src="assets/browser-code-session.png" alt="Native Codex browser session in FCC, showing model controls and a repository exploration" width="700">
<p><em>A native Codex session in FCC's browser UI.</em></p>
</div>
<div align="center">
<img src="assets/admin-page.png" alt="Free Claude Code Admin UI" width="700">
</div>
<div align="center">
<img src="assets/cc-model-picker.png" alt="Claude Code model picker showing FCC models" width="700">
<p><em>Select an FCC model from Claude Code's native <code>/model</code> picker.</em></p>
</div>
<details>
<summary><strong>Provider catalog</strong></summary>
</details>
<details>
<summary><strong>Provider-specific setup</strong></summary>
</details>
<details>
<summary><strong>Local provider setup</strong></summary>
</details>
<details>
<summary><strong>Optional model-tier routing</strong></summary>
</details>
<details>
<summary><strong>Reasoning control</strong></summary>
</details>
<details>
<summary><strong>Discord bot</strong></summary>
</details>
<details>
<summary><strong>Telegram bot</strong></summary>
</details>
<details>
<summary><strong>Voice notes</strong></summary>
</details>
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.
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.
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!
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.
Quick Start
<a id="install"></a>
1. Install
macOS/Linux:
curl -fsSL "https://raw.githubusercontent.com/Alishahryar1/free-claude-code/main/scripts/install.sh" | sh
When prompted, choose at least one coding agent and optionally enable RTK + Headroom token optimization for supported agents.
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-server
FCC 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.
Open NVIDIA NIM in Providers, click Add key, paste the key, and click Save.
Leave MODEL on the default nvidia_nim/nvidia/nemotron-3-super-120b-a12b, or search the model dropdown and select another model.
Click Apply to save your model selection.
To protect the local proxy with a bearer token, enable Proxy Authentication
in Admin.
4. Run Your Coding Agent
Claude Code:
fcc-claude
Codex:
fcc-codex
Pi:
fcc-pi
OpenCode 2:
fcc-opencode
Cline:
fcc-cline
Hermes:
fcc-hermes
DeepSeek Harness Web:
fcc-dsh
Grok Build:
fcc-grok
Muse Code:
fcc-muse
Aider:
fcc-aider
<a id="model-picker"></a>
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 MODEL dropdown 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.
Provider modals support numbered API keys. Use Add key, remove rows, or drag their handles to reorder them. FCC uses key 1.
For another API endpoint, open Providers → Custom providers → Add provider. Enter its API base URL, optional keys, 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.
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.
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_URL to its complete v1 endpoint, such as
https://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 use
kimi/. 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_URL to 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
use qwencloud/. 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_KEY but use the explicit
opencode_zen/ and opencode_go/ model prefixes.
For Amazon Bedrock, set BEDROCK_BASE_URL to 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 login once. Service-account
files and attached service accounts also work. Set VERTEX_PROJECT_ID, and
optionally change VERTEX_LOCATION from its global default.
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.
FCC automatically discovers models from running local servers at startup. If you start a server later, click Refresh models in Admin to add its models to the picker.
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 serve
Use the tag shown by ollama list with the ollama/ prefix. OLLAMA_BASE_URL defaults to http://localhost:11434.
Provider cards show the checked endpoint and response time, with a useful message when a local server is unavailable. After starting the server or correcting its settings, click Test to refresh its models.
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, effort, and API key number in the bottom row, then click +. Key 1, Key 2, and so on refer to the current numbered keys in that provider's settings. Edit the selections 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. You can select the same model with another key number.
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. |
<a id="connect-your-client"></a>
Connect Your Client
FCC launchers automatically start the server.
For editor and app integrations, install the client, start FCC, then open
Admin UI → Integrations and click Connect on its card.
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.
<a id="optional-integrations"></a>
Optional Integrations
Configure integrations from Admin UI → Messaging, then click Apply.
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. |
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-local
Local 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 cu130
After 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-update
The update installs the checked stable FCC release with its matching installer.
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.
