claude-code-gpt-5: A Python repository from teremterem

This repository lets you use Anthropic's Claude Code CLI with OpenAI's GPT-5 via a local LiteLLM proxy.

Quick Start ⚡

Prerequisites

OpenAI API key 🔑
Anthropic API key - optional 🔑

About the Anthropic API key

By default, the provided .env template (.env.template that you will have to copy to .env) remaps Claude models (haiku/sonnet/opus) to GPT‑5 equivalents, so all requests go to OpenAI. If you want to keep using Anthropic for any calls, set ANTHROPIC_API_KEY and adjust the REMAP_* variables in .env (or set some/all of them to empty strings).

First time using GPT-5 via API?

If you are going to use GPT-5 via API for the first time, OpenAI may require you to verify your identity via Persona. You may encounter an OpenAI error asking you to “verify your organization.” To resolve this, you can go through the verification process here:

OpenAI developer platform - Organization settings

Setup 🛠️

Clone this repository:

git clone https://github.com/teremterem/claude-code-gpt-5.git
cd claude-code-gpt-5

Install uv (if you haven't already):

macOS/Linux:

curl -LsSf https://astral.sh/uv/install.sh | sh

macOS (using Homebrew):

brew install uv

Windows (using PowerShell):

powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Windows (using Scoop):

scoop install uv

Alternative: pip install

pip install uv

Configure Environment Variables: Copy the template file to create your .env:

cp .env.template .env

Edit .env and add your API keys:

OPENAI_API_KEY=your-openai-api-key-here
# Optional: only needed if you plan to use Anthropic models
# ANTHROPIC_API_KEY=your-anthropic-api-key-here

# Recommended: remap Claude models to GPT‑5 variants to ensure all
# built-in agents in Claude Code also use GPT‑5
REMAP_CLAUDE_HAIKU_TO=gpt-5-nano-reason-minimal
REMAP_CLAUDE_SONNET_TO=gpt-5-reason-medium
REMAP_CLAUDE_OPUS_TO=gpt-5-reason-high

# Some more optional settings (see .env.template for details)
...

Run the server:
```
uv run litellm --config config.yaml
```

Using with Claude Code 🎮

Install Claude Code (if you haven't already):
```
npm install -g @anthropic-ai/claude-code
```
Connect to your proxy to use GPT-5 variants:
```
ANTHROPIC_BASE_URL=http://localhost:4000 claude
```
Alternatively, you can override the default model on the side of the CLI using the --model parameter:
```
ANTHROPIC_BASE_URL=http://localhost:4000 claude --model gpt-5-reason-medium
```
That's it! Your Claude Code client will now use the selected GPT-5 variant with your chosen reasoning effort level. 🎯

Available GPT-5 model aliases

GPT-5:
- gpt-5-reason-minimal
- gpt-5-reason-low
- gpt-5-reason-medium
- gpt-5-reason-high
GPT-5-mini:
- gpt-5-mini-reason-minimal
- gpt-5-mini-reason-low
- gpt-5-mini-reason-medium
- gpt-5-mini-reason-high
GPT-5-nano:
- gpt-5-nano-reason-minimal
- gpt-5-nano-reason-low
- gpt-5-nano-reason-medium
- gpt-5-nano-reason-high

NOTE: Generally, you can use arbitrary models from arbitrary providers, but for providers other than OpenAI or Anthropic, you will need to specify the provider in the model name, e.g. gemini/gemini-pro, gemini/gemini-pro-reason-disable etc. (as well as set the respective API keys along with any other environment variables that the provider might require in your .env file).

KNOWN PROBLEM

The Web Search tool currently does not work with this setup. You may see an error like:

API Error (500 {"error":{"message":"Error calling litellm.acompletion for non-Anthropic model: litellm.BadRequestError: OpenAIException - Invalid schema for function 'web_search': 'web_search_20250305' is not valid under any of the given schemas.","type":"None","param":"None","code":"500"}}) · Retrying in 1 seconds… (attempt 1/10)

This is planned to be fixed soon.

NOTE: The Fetch tool (getting web content from specific URLs) is not affected and works normally.