claude-code-proxy
Connect Claude Code to alternative models from OpenAI or Gemini.
Forked from: 1rgs/claude-code-proxy
Quick start
uvx claude-code-proxy
Installation
Prerequisites
- Set
OPENAI_API_KEYorGEMINI_API_KEYin your environment. - Install
uv:- Install docs here: https://docs.astral.sh/uv/getting-started/installation
- On MacOS:
brew install uv - On Windows:
winget install astral-sh.uv
Configuration
-
Configure Environment Variables: Copy the example environment file:
cp .env.example .env
Edit
.envand fill in your API keys and model configurations:ANTHROPIC_API_KEY: (Optional) Needed only if proxying to Anthropic models.OPENAI_API_KEY: Your OpenAI API key (Required if using the default OpenAI preference or as fallback).GEMINI_API_KEY: Your Google AI Studio (Gemini) API key (Required if PREFERRED_PROVIDER=google).PREFERRED_PROVIDER(Optional): Set toopenai(default) orgoogle. This determines the primary backend for mappinghaiku/sonnet.BIG_MODEL(Optional): The model to mapsonnetrequests to. Defaults togpt-4.1(ifPREFERRED_PROVIDER=openai) orgemini-2.5-pro-preview-03-25.SMALL_MODEL(Optional): The model to maphaikurequests to. Defaults togpt-4.1-mini(ifPREFERRED_PROVIDER=openai) orgemini-2.0-flash.
Mapping Logic:
- If
PREFERRED_PROVIDER=openai(default),haiku/sonnetmap toSMALL_MODEL/BIG_MODELprefixed withopenai/. - If
PREFERRED_PROVIDER=google,haiku/sonnetmap toSMALL_MODEL/BIG_MODELprefixed withgemini/if those models are in the server's knownGEMINI_MODELSlist (otherwise falls back to OpenAI mapping).
-
Run the server:
uv run uvicorn server:app --host 0.0.0.0 --port 8082 --reload
(
--reloadis optional, for development)
Using with Claude Code 🎮
-
Install Claude Code (if you haven't already):
npm install -g @anthropic-ai/claude-code
-
Connect to your proxy:
ANTHROPIC_BASE_URL=http://localhost:8082 claude
-
That's it! Your Claude Code client will now use the configured backend models (defaulting to Gemini) through the proxy. 🎯
Model Mapping 🗺️
The proxy automatically maps Claude models to either OpenAI or Gemini models based on the configured model:
| Claude Model | Default Mapping | When BIG_MODEL/SMALL_MODEL is a Gemini model |
|---|---|---|
| haiku | openai/gpt-4o-mini | gemini/[model-name] |
| sonnet | openai/gpt-4o | gemini/[model-name] |
Supported Models
OpenAI Models
The following OpenAI models are supported with automatic openai/ prefix handling:
- o3-mini
- o1
- o1-mini
- o1-pro
- gpt-4.5-preview
- gpt-4o
- gpt-4o-audio-preview
- chatgpt-4o-latest
- gpt-4o-mini
- gpt-4o-mini-audio-preview
- gpt-4.1
- gpt-4.1-mini
Gemini Models
The following Gemini models are supported with automatic gemini/ prefix handling:
- gemini-2.5-pro-preview-03-25
- gemini-2.0-flash
Model Prefix Handling
The proxy automatically adds the appropriate prefix to model names:
- OpenAI models get the
openai/prefix - Gemini models get the
gemini/prefix - The BIG_MODEL and SMALL_MODEL will get the appropriate prefix based on whether they're in the OpenAI or Gemini model lists
For example:
gpt-4obecomesopenai/gpt-4ogemini-2.5-pro-preview-03-25becomesgemini/gemini-2.5-pro-preview-03-25- When BIG_MODEL is set to a Gemini model, Claude Sonnet will map to
gemini/[model-name]
Customizing Model Mapping
Control the mapping using environment variables in your .env file or directly:
Example 1: Default (Use OpenAI)
No changes needed in .env beyond API keys, or ensure:
OPENAI_API_KEY="your-openai-key"
GEMINI_API_KEY="your-google-key" # Needed if PREFERRED_PROVIDER=google
# PREFERRED_PROVIDER="openai" # Optional, it's the default
# BIG_MODEL="gpt-4.1" # Optional, it's the default
# SMALL_MODEL="gpt-4.1-mini" # Optional, it's the default
Example 2: Prefer Google
GEMINI_API_KEY="your-google-key"
OPENAI_API_KEY="your-openai-key" # Needed for fallback
PREFERRED_PROVIDER="google"
# BIG_MODEL="gemini-2.5-pro-preview-03-25" # Optional, it's the default for Google pref
# SMALL_MODEL="gemini-2.0-flash" # Optional, it's the default for Google pref
Example 3: Use Specific OpenAI Models
OPENAI_API_KEY="your-openai-key"
GEMINI_API_KEY="your-google-key"
PREFERRED_PROVIDER="openai"
BIG_MODEL="gpt-4o" # Example specific model
SMALL_MODEL="gpt-4o-mini" # Example specific model
How It Works 🧩
This proxy works by:
- Receiving requests in Anthropic's API format 📥
- Translating the requests to OpenAI format via LiteLLM 🔄
- Sending the translated request to OpenAI 📤
- Converting the response back to Anthropic format 🔄
- Returning the formatted response to the client ✅
The proxy handles both streaming and non-streaming responses, maintaining compatibility with all Claude clients. 🌊
Contributing 🤝
Contributions are welcome! Please feel free to submit a Pull Request. 🎁
Metadata
Release files for claude-code-proxy 0.1.5
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| claude_code_proxy-0.1.5.tar.gz | 16.8 kB | Without provenance | Details for claude_code_proxy-0.1.5.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| claude_code_proxy-0.1.5-py3-none-any.whl | Python 3 | none | any | Details for claude_code_proxy-0.1.5-py3-none-any.whl |
Total release size: 35.0 kB
Release files / claude_code_proxy-0.1.5.tar.gz
| Download URL | claude_code_proxy-0.1.5.tar.gz |
|---|---|
| Size | 16.8 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
4234b19ed9e0dadd7ecd430adbc2728aa374771f32bb0f1530b5d4e6e63627e2
|
|
BLAKE2b-256 checksum How to use checksums |
ec3bfa61383655deab9f2146a68dbf0007b8cdbf5401abf26f354f219f38f1fb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.7.8
|
Release files / claude_code_proxy-0.1.5-py3-none-any.whl
| Download URL | claude_code_proxy-0.1.5-py3-none-any.whl |
|---|---|
| Size | 18.2 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
0e410a4ce6332dfc1fcc8d63c6ab6304a032c0d3744678dd5628c67eefbad897
|
|
BLAKE2b-256 checksum How to use checksums |
1c97bcd53d9c45c6866c8b076beb2d133eb2fad8b4317aa0bd98011a78976e82
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
uv/0.7.8
|
Security for claude-code-proxy 0.1.5
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.