claude-code-proxy

claude-code-proxy lets you use Claude Code with your ChatGPT Plus/Pro subscription or your Kimi Code (kimi.com) account.

Quick start · Providers · How it works · Configuration · Limitations

Why?

I feel Claude Code is still the best harness around, despite occasional frustrations caused by updates. However, Anthropic keeps tightening the usage limits, while OpenAI is still much more generous.

If you want to use OpenAI plans, your best options seem to be OpenCode and Codex. I tried OpenCode, but the UX has many rough edges, especially around skills feeling like a second-class feature. Fortunately it's open source and I ended up forking it and applying some patches, but would much rather not do it.

Quick start

1. Install

Homebrew (macOS and Linux):

brew install raine/claude-code-proxy/claude-code-proxy

Install script (macOS and Linux):

curl -fsSL https://raw.githubusercontent.com/raine/claude-code-proxy/main/scripts/install.sh | bash

Manual: download a prebuilt binary for your platform from the releases page.

2. Pick a provider and authenticate

The proxy supports two upstream providers. Pick one and run its login flow; the proxy will refuse to start traffic until a token is stored.

Codex (ChatGPT Plus/Pro):

claude-code-proxy codex auth login     # browser OAuth (PKCE)
# or, on a headless machine:
claude-code-proxy codex auth device    # device-code flow

Sign in with your ChatGPT Plus/Pro account, not an OpenAI API account.

Kimi (kimi.com Kimi Code):

claude-code-proxy kimi auth login      # device-code flow (prints URL + code)

Sign in with your kimi.com account. The verification URL is displayed; open it in any browser, confirm the code, and the CLI polls until done.

On macOS credentials go to Keychain; on other platforms they are written to ~/.config/claude-code-proxy/<provider>/auth.json (mode 0600).

Verify:

claude-code-proxy codex auth status
claude-code-proxy kimi auth status

3. Start the proxy

claude-code-proxy serve                # listens on 127.0.0.1:18765
PORT=11435 claude-code-proxy serve     # change the listen port

Binds to 127.0.0.1 only. One serve process handles all providers — the upstream for each request is chosen from ANTHROPIC_MODEL.

4. Point Claude Code at it

ANTHROPIC_MODEL selects the provider:

gpt-5.4, gpt-5.3-codex, gpt-5.4-mini, gpt-5.2 → codex
kimi-for-coding, kimi-k2.6, k2.6 → kimi

An unknown model returns a 400 listing the supported ids. There is no implicit default provider.

Claude Code also issues background requests (session title generation, token counts) against its built-in "small/fast" haiku model id. Those requests would 400 because no provider claims it, so set ANTHROPIC_SMALL_FAST_MODEL to a concrete id too (the same value as ANTHROPIC_MODEL is usually fine):

# Codex
ANTHROPIC_BASE_URL=http://localhost:18765 \
ANTHROPIC_AUTH_TOKEN=unused \
ANTHROPIC_MODEL=gpt-5.4 \
ANTHROPIC_SMALL_FAST_MODEL=gpt-5.4-mini \
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 \
  claude

# Kimi
ANTHROPIC_BASE_URL=http://localhost:18765 \
ANTHROPIC_AUTH_TOKEN=unused \
ANTHROPIC_MODEL=kimi-for-coding \
ANTHROPIC_SMALL_FAST_MODEL=kimi-for-coding \
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 \
  claude

Or set it persistently in ~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_BASE_URL": "http://127.0.0.1:18765",
    "ANTHROPIC_AUTH_TOKEN": "unused",
    "ANTHROPIC_MODEL": "gpt-5.4",
    "ANTHROPIC_SMALL_FAST_MODEL": "gpt-5.4-mini",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1
  }
}

5. Optional: disable Claude Code auto-compact

Claude Code decides auto-compaction locally based on the model context window it thinks it has. If the upstream model supports a larger window than Claude Code assumes, it may compact earlier than necessary.

Disable only automatic compaction while keeping manual /compact available:

DISABLE_AUTO_COMPACT=1 \
ANTHROPIC_BASE_URL=http://localhost:18765 \
ANTHROPIC_AUTH_TOKEN=unused \
ANTHROPIC_MODEL=gpt-5.4 \
ANTHROPIC_SMALL_FAST_MODEL=gpt-5.4-mini \
CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1 \
  claude

Or add it to ~/.claude/settings.json:

{
  "env": {
    "ANTHROPIC_BASE_URL": "http://127.0.0.1:18765",
    "ANTHROPIC_AUTH_TOKEN": "unused",
    "ANTHROPIC_MODEL": "gpt-5.4",
    "ANTHROPIC_SMALL_FAST_MODEL": "gpt-5.4-mini",
    "CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC": 1,
    "DISABLE_AUTO_COMPACT": 1
  }
}

Tradeoffs:

Claude Code will stop proactively compacting before a turn.
Manual /compact still works.
If you let the session grow too far, you may hit prompt-too-long failures instead of a graceful auto-compact.

Providers

Codex (ChatGPT)

Upstream: https://chatgpt.com/backend-api/codex/responses (Responses API).

Set ANTHROPIC_MODEL to a model your ChatGPT subscription is allowed to use. Confirmed working on Plus:

gpt-5.4
gpt-5.3-codex

Also verified:

gpt-5.2
gpt-5.4-mini

If the resolved model isn't supported by your account, upstream returns a 400 like "The 'gpt-4.1' model is not supported when using Codex with a ChatGPT account.". The proxy surfaces that verbatim.

Auth:

Command	What it does
`codex auth login`	Browser OAuth (PKCE) via `auth.openai.com`
`codex auth device`	Device-code OAuth for headless machines
`codex auth status`	Show account ID + token expiry
`codex auth logout`	Delete stored credentials

Kimi (Kimi Code)

Upstream: https://api.kimi.com/coding/v1/chat/completions (OpenAI-style chat-completions).

Only one wire model is exposed: kimi-for-coding (its display name in kimi-cli is Kimi-k2.6, 256k context, supports reasoning + image input + video input). kimi-k2.6 and k2.6 are accepted as aliases for the same wire id.

Reasoning effort: Claude Code's output_config.effort value (the one you see in the UI as ◐ medium · /effort) is forwarded as Kimi's reasoning_effort (low / medium / high). Thinking blocks from the upstream model are forwarded to Claude Code and rendered as thinking content. If Claude Code disables thinking, the proxy drops both reasoning_effort and the thinking: {type: "enabled"} flag before forwarding.

Auth:

Command	What it does
`kimi auth login`	Device-code OAuth via `auth.kimi.com`
`kimi auth status`	Show user ID + token expiry
`kimi auth logout`	Delete stored credentials

How it works

sequenceDiagram
    autonumber
    participant CC as Claude Code
    participant P as claude-code-proxy
    participant AUTH as OAuth host<br/>(auth.openai.com or<br/>auth.kimi.com)
    participant U as Upstream API<br/>(chatgpt.com/codex or<br/>api.kimi.com)

    Note over P,AUTH: One-time: PKCE / device OAuth<br/>tokens cached locally for reuse

    CC->>P: POST /v1/messages (Anthropic shape, stream: true)

    alt access token expiring
        P->>AUTH: POST /oauth/token (refresh_token)
        AUTH-->>P: new access (+ rotated refresh)
    end

    P->>P: translate request<br/>• strip Anthropic-only fields<br/>• system blocks → instructions / system message<br/>• tool_use / tool_result ↔ provider-specific shapes<br/>• prompt_cache_key = session id
    P->>U: POST upstream<br/>Bearer + provider-specific headers
    U-->>P: provider SSE<br/>(Codex: output_item.*, output_text.delta, …)<br/>(Kimi: chat.completion.chunk, reasoning_content, …)
    P->>P: reducer: typed events<br/>(thinking / text / tool start/delta/stop, finish)
    P-->>CC: Anthropic SSE<br/>(message_start, content_block_*, message_delta, message_stop)

Commands

Command	Description
`serve`	Start the proxy on `PORT`
`codex auth login` / `device` / `status` / `logout`	Codex OAuth management
`kimi auth login` / `status` / `logout`	Kimi OAuth management

`serve`

Starts the HTTP proxy and blocks. Binds to 127.0.0.1 only. Logs to $XDG_STATE_HOME/claude-code-proxy/proxy.log (rotated at 20 MiB). Set CCP_LOG_STDERR=1 to mirror log lines to stderr while running.

claude-code-proxy serve
PORT=11435 claude-code-proxy serve
CCP_LOG_STDERR=1 claude-code-proxy serve

Prints the supported model → provider mapping on startup. One serve process dispatches to any provider based on the model field in each request. Requests whose model isn't registered with any provider are rejected with HTTP 400 listing the supported ids.

Codex auth commands

`codex auth login`

Runs the PKCE browser flow against auth.openai.com using the Codex CLI's client ID. Prints a URL, opens a local callback listener on port 1455, waits for the browser to redirect back, and stores the resulting access / refresh tokens in Keychain on macOS or locally on other platforms. The process exits automatically once the tokens are saved.

claude-code-proxy codex auth login

Sign in with your ChatGPT Plus/Pro account, not an OpenAI API account. The token file includes the extracted chatgpt_account_id so the proxy can set the ChatGPT-Account-Id header on every upstream call.

`codex auth device`

Same OAuth flow, but for headless machines. Prints a short user code and a URL; you enter the code from any browser on any other device, and the CLI polls auth.openai.com until you authorize, then stores the token.

claude-code-proxy codex auth device

Useful over SSH, inside a container, or on any host that can't open a browser.

`codex auth status`

Shows whether credentials are stored, the account ID, and how long until the access token expires. Non-zero exit if no auth is present.

claude-code-proxy codex auth status

Example output:

Account: 79342a5e-57b7-44ea-bfdc-a83ba070dad6
Expires: 2026-04-28T16:46:04.827Z (in 863946s)
Storage: macOS Keychain

The proxy refreshes the access token 5 minutes before expiry with a single-flight guard, so concurrent requests never trigger stampedes of refresh calls.

`codex auth logout`

Removes stored auth credentials. On macOS this deletes the Keychain entry. No server call is needed; the refresh token just becomes dead.

claude-code-proxy codex auth logout

Run codex auth login again to re-authenticate.

Kimi auth commands

`kimi auth login`

Runs a device-code OAuth flow (RFC 8628) against auth.kimi.com using the kimi-cli client ID. Prints a verification URL and a short user code; open the URL in any browser, confirm the code, and the CLI polls until the tokens are issued. Tokens are stored in Keychain on macOS or a mode-0600 file elsewhere.

claude-code-proxy kimi auth login

Sign in with your kimi.com account. The access token has a ~15 minute lifetime; the proxy refreshes it 5 minutes before expiry with a single-flight guard and persists the rotated refresh token.

A persistent device ID is generated on first login at ~/.config/claude-code-proxy/kimi/device_id and reused forever — it's bound into the issued JWT, so rotating it would invalidate your token.

`kimi auth status`

claude-code-proxy kimi auth status

Shows the user ID extracted from the token, expiry time, scope, and storage backend. Non-zero exit if no auth is present.

`kimi auth logout`

claude-code-proxy kimi auth logout

Removes stored auth credentials (Keychain entry on macOS, file elsewhere). Run kimi auth login again to re-authenticate.

Endpoints

The proxy speaks enough of the Anthropic API for Claude Code:

POST /v1/messages: the main turn endpoint (streaming and non-streaming)
POST /v1/messages?beta=true: same (Claude Code always sends ?beta=true)
POST /v1/messages/count_tokens: local token count via gpt-tokenizer (o200k_base); used by Claude Code's compaction logic
GET /healthz: liveness check

Configuration

Settings are environment variables on the proxy process, not a config file.

Variable	Default	Purpose
`PORT`	`18765`	Proxy listen port
`XDG_STATE_HOME`	`~/.local/state`	Base dir for `proxy.log`
`CCP_LOG_STDERR`	unset	Also mirror log lines to stderr
`CCP_LOG_VERBOSE`	unset	Log full request/response bodies + every SSE event
`KIMI_OAUTH_HOST`	`https://auth.kimi.com`	Override Kimi's OAuth host (debugging only)
`KIMI_BASE_URL`	`https://api.kimi.com/coding/v1`	Override Kimi's API base URL

Files

$XDG_STATE_HOME/claude-code-proxy/proxy.log — JSON-lines log, rotated at 20 MiB. Secrets (authorization, access, refresh, id_token, ChatGPT-Account-Id, …) are redacted before write.
~/.config/claude-code-proxy/codex/auth.json — codex tokens (non-macOS; macOS uses Keychain under service claude-code-proxy.codex).
~/.config/claude-code-proxy/kimi/auth.json — kimi tokens (non-macOS; macOS uses Keychain under service claude-code-proxy.kimi).
~/.config/claude-code-proxy/kimi/device_id — persistent UUID bound into the Kimi JWT at login. Reused for the lifetime of the install.

Limitations

Terms of service: using the Codex or Kimi backends from a non-official client is a gray area. Use at your own risk.
Rate limits: shared across all clients of your upstream account. Codex's codex.rate_limits.limit_reached and Kimi's HTTP 429 are both surfaced as HTTP 429 with retry-after.
Codex — image inputs in tool results: Responses API function_call_output only takes a string, so image blocks nested inside tool_result are replaced with a [image omitted: <media_type>] placeholder. Top-level user-message images pass through.
Kimi — image inputs in tool results: pass through as image_url parts (Kimi accepts them in role:"tool" content).
Codex — reasoning blocks: not forwarded to Claude Code (dropped), even if the upstream model produced them.
Kimi — reasoning blocks: forwarded as Anthropic thinking content blocks and rendered by Claude Code. Disable by setting thinking: {"type":"disabled"} in your Anthropic request.
Session title generation: Claude Code's parallel title-gen request is forwarded upstream like any other structured-output request. This costs a handful of tokens per session rather than being stubbed.
Codex — output_config.format: translated to Responses API text.format (json_schema with strict: true); other Anthropic-specific output_config fields are dropped.

Development

bunx tsc --noEmit                          # typecheck
bun src/cli.ts serve                       # run locally (routes all providers)
tail -f ~/.local/state/claude-code-proxy/proxy.log | jq .

Install a compiled dev build globally: compile the current working tree to a binary and place it on your PATH without linking:

mkdir -p ~/.local/bin
bun build ./src/cli.ts --compile --outfile ~/.local/bin/claude-code-proxy

Related projects

claude-history: search Claude Code conversation history from the terminal
git-surgeon: non-interactive hunk-level git staging for AI agents
workmux: manage parallel AI coding tasks in separate git worktrees with tmux
consult-llm-mcp: MCP server for consulting external LLMs (Gemini, Codex, etc.) from inside Claude Code

Name		Name	Last commit message	Last commit date
Latest commit History 70 Commits
.github/workflows		.github/workflows
meta		meta
scripts		scripts
src		src
.gitignore		.gitignore
CHANGELOG.md		CHANGELOG.md
LICENSE		LICENSE
README.md		README.md
bun.lock		bun.lock
package.json		package.json
tsconfig.json		tsconfig.json

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Repository files navigation

claude-code-proxy

Why?

Quick start

1. Install

2. Pick a provider and authenticate

3. Start the proxy

4. Point Claude Code at it

5. Optional: disable Claude Code auto-compact

Providers

Codex (ChatGPT)

Kimi (Kimi Code)

How it works

Commands

`serve`

Codex auth commands

`codex auth login`

`codex auth device`

`codex auth status`

`codex auth logout`

Kimi auth commands

`kimi auth login`

`kimi auth status`

`kimi auth logout`

Endpoints

Configuration

Files

Limitations

Development

Related projects

About

Uh oh!

Releases 4

Contributors 1

Languages

Folders and files

Latest commit

History

Repository files navigation

claude-code-proxy

Why?

Quick start

1. Install

2. Pick a provider and authenticate

3. Start the proxy

4. Point Claude Code at it

5. Optional: disable Claude Code auto-compact

Providers

Codex (ChatGPT)

Kimi (Kimi Code)

How it works

Commands

serve

Codex auth commands

codex auth login

codex auth device

codex auth status

codex auth logout

Kimi auth commands

kimi auth login

kimi auth status

kimi auth logout

Endpoints

Configuration

Files

Limitations

Development

Related projects

About

Resources

License

Uh oh!

Stars

Watchers

Forks

Releases 4

Contributors 1

Languages

`serve`

`codex auth login`

`codex auth device`

`codex auth status`

`codex auth logout`

`kimi auth login`

`kimi auth status`

`kimi auth logout`