# Server portport: 8317# Management API settingsremote-management: # Whether to allow remote (non-localhost) management access. # When false, only localhost can access management endpoints (a key is still required). allow-remote: false # Management key. If a plaintext value is provided here, it will be hashed on startup. # All management requests (even from localhost) require this key. # Leave empty to disable the Management API entirely (404 for all /v0/management routes). secret-key: ""# Authentication directory (supports ~ for home directory)auth-dir: "~/.cli-proxy-api"# Enable debug loggingdebug: false# Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/proxy-url: ""# Number of times to retry a request. Retries will occur if the HTTP response code is 403, 408, 500, 502, 503, or 504.request-retry: 3# Quota exceeded behaviorquota-exceeded: switch-project: true # Whether to automatically switch to another project when a quota is exceeded switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded# API keys for authenticationapi-keys: - "your-api-key-1" - "your-api-key-2"# API keys for official Generative Language APIgenerative-language-api-key: - "AIzaSy...01" - "AIzaSy...02" - "AIzaSy...03" - "AIzaSy...04"# forces the use of GPT-5 Codex model.force-gpt-5-codex: true# Codex API keyscodex-api-key: - api-key: "sk-atSM..." base-url: "https://www.example.com" # use the custom codex API endpoint# Claude API keysclaude-api-key: - api-key: "sk-atSM..." # use the official claude API key, no need to set the base url - api-key: "sk-atSM..." base-url: "https://www.example.com" # use the custom claude API endpoint# OpenAI compatibility providersopenai-compatibility: - name: "openrouter" # The name of the provider; it will be used in the user agent and other places. base-url: "https://openrouter.ai/api/v1" # The base URL of the provider. api-keys: # The API keys for the provider. Add multiple keys if needed. Omit if unauthenticated access is allowed. - "sk-or-v1-...b780" - "sk-or-v1-...b781" models: # The models supported by the provider. - name: "moonshotai/kimi-k2:free" # The actual model name. alias: "kimi-k2" # The alias used in the API.# Gemini Web settings# gemini-web:# # Conversation reuse: set to true to enable (default), false to disable.# context: true# # Maximum characters per single request to Gemini Web. Requests exceeding this# # size split into chunks. Only the last chunk carries files and yields the final answer.# max-chars-per-request: 1000000# # Disable the short continuation hint appended to intermediate chunks# # when splitting long prompts. Default is false (hint enabled by default).# disable-continuation-hint: false# # Background token auto-refresh interval seconds (defaults to 540 if unset or <= 0)# token-refresh-seconds: 540# # Code mode:# # - true: enable XML wrapping hint and attach the coding-partner Gem.# # Thought merging (<think> into visible content) applies to STREAMING only;# # non-stream responses keep reasoning/thought parts separate for clients# # that expect explicit reasoning fields.# # - false: disable XML hint and keep <think> separate# code-mode: false
# Server port
port: 8317
# Management API settings
remote-management:
# Whether to allow remote (non-localhost) management access.
# When false, only localhost can access management endpoints (a key is still required).
allow-remote: false
# Management key. If a plaintext value is provided here, it will be hashed on startup.
# All management requests (even from localhost) require this key.
# Leave empty to disable the Management API entirely (404 for all /v0/management routes).
secret-key: ""
# Authentication directory (supports ~ for home directory)
auth-dir: "~/.cli-proxy-api"
# Enable debug logging
debug: false
# Proxy URL. Supports socks5/http/https protocols. Example: socks5://user:pass@192.168.1.1:1080/
proxy-url: ""
# Number of times to retry a request. Retries will occur if the HTTP response code is 403, 408, 500, 502, 503, or 504.
request-retry: 3
# Quota exceeded behavior
quota-exceeded:
switch-project: true # Whether to automatically switch to another project when a quota is exceeded
switch-preview-model: true # Whether to automatically switch to a preview model when a quota is exceeded
# API keys for authentication
api-keys:
- "your-api-key-1"
- "your-api-key-2"
# API keys for official Generative Language API
generative-language-api-key:
- "AIzaSy...01"
- "AIzaSy...02"
- "AIzaSy...03"
- "AIzaSy...04"
# forces the use of GPT-5 Codex model.
force-gpt-5-codex: true
# Codex API keys
codex-api-key:
- api-key: "sk-atSM..."
base-url: "https://www.example.com" # use the custom codex API endpoint
# Claude API keys
claude-api-key:
- api-key: "sk-atSM..." # use the official claude API key, no need to set the base url
- api-key: "sk-atSM..."
base-url: "https://www.example.com" # use the custom claude API endpoint
# OpenAI compatibility providers
openai-compatibility:
- name: "openrouter" # The name of the provider; it will be used in the user agent and other places.
base-url: "https://openrouter.ai/api/v1" # The base URL of the provider.
api-keys: # The API keys for the provider. Add multiple keys if needed. Omit if unauthenticated access is allowed.
- "sk-or-v1-...b780"
- "sk-or-v1-...b781"
models: # The models supported by the provider.
- name: "moonshotai/kimi-k2:free" # The actual model name.
alias: "kimi-k2" # The alias used in the API.
# Gemini Web settings
# gemini-web:
# # Conversation reuse: set to true to enable (default), false to disable.
# context: true
# # Maximum characters per single request to Gemini Web. Requests exceeding this
# # size split into chunks. Only the last chunk carries files and yields the final answer.
# max-chars-per-request: 1000000
# # Disable the short continuation hint appended to intermediate chunks
# # when splitting long prompts. Default is false (hint enabled by default).
# disable-continuation-hint: false
# # Background token auto-refresh interval seconds (defaults to 540 if unset or <= 0)
# token-refresh-seconds: 540
# # Code mode:
# # - true: enable XML wrapping hint and attach the coding-partner Gem.
# # Thought merging (<think> into visible content) applies to STREAMING only;
# # non-stream responses keep reasoning/thought parts separate for clients
# # that expect explicit reasoning fields.
# # - false: disable XML hint and keep <think> separate
# code-mode: false