Sign In
Open your user center to view only your own balance, access, and usage.
✦ QUICK START
Start in Three Steps
Issue a Key
Name the key, set its limits, and use every enabled model.
Switch the URL
Set the API Base URL in your client and keep its native protocol.
API Integration Guide
Choose an agent setup or call a native API directly. Every example uses the same LuckyAPI key.
Before you startSign in to the Console, issue an API key, then replace YOUR_API_KEY in an example below.
https://luckyapi.online
Authorization: Bearer YOUR_API_KEY
Use a switcher for the easiest setup, or configure a supported client manually.
Recommended
CC Switch
A graphical provider switcher is the simplest option for Codex and Claude Code.
- 1
Open CC Switch and add a custom provider.
- 2
Choose Codex or Claude, then enter the matching Base URL below.
- 3
Enter your LuckyAPI key and activate the provider.
- 4
Restart the target app if it was already running.
- Codex
https://luckyapi.online/v1- Claude Code
https://luckyapi.online- API Key
YOUR_API_KEY
Shared configuration
Codex CLI / Desktop
Codex CLI and Codex Desktop use the same user-level configuration when they run as the same system user with the same CODEX_HOME.
Save the file, then restart Codex Desktop or start a new Codex CLI session.
Configuration file
~/.codex/config.toml
model = "gpt-5.6-sol"
model_provider = "relay"
[model_providers.relay]
name = "LuckyAPI"
base_url = "https://luckyapi.online/v1"
wire_api = "responses"
requires_openai_auth = false
experimental_bearer_token = "YOUR_API_KEY"Claude Code
Set the native Claude Code endpoint and authentication token once in its user settings.
Configuration file
~/.claude/settings.json
{
"env": {
"ANTHROPIC_BASE_URL": "https://luckyapi.online",
"ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY"
}
}Restart the client after saving the configuration.
One-session setup
Kimi Code
Use Kimi Code's official KIMI_MODEL_* channel to connect one session without changing its persistent configuration.
Run in Terminal
KIMI_MODEL_NAME="k3" \
KIMI_MODEL_API_KEY="YOUR_API_KEY" \
KIMI_MODEL_PROVIDER_TYPE="kimi" \
KIMI_MODEL_BASE_URL="https://luckyapi.online/v1" \
kimiThis setup lasts only for the current launch. Use the Direct API tab if you are integrating an application.
Grok CLI
Grok CLI uses a namespaced Base URL so its model list does not conflict with Codex.
Run in Terminal
export GROK_MODELS_BASE_URL="https://luckyapi.online/v1/grok"
export XAI_API_KEY="YOUR_API_KEY"
grok models
grokKeep /v1/grok in the Base URL. Pointing Grok CLI at /v1 would read the Codex model catalog.
LuckyAPI preserves each provider's native protocol. Choose the matching endpoint instead of forcing every model through one schema.
OpenAI Responses
GPT / Codex
POST /v1/responsesUse the native Responses API for GPT text and agent requests.
curl https://luckyapi.online/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-5.6-sol","input":"Say hello in one sentence."}'Model catalog: GET /v1/models
OpenAI Images
GPT Image
POST /v1/images/generationsImage generation can take longer than text requests, so allow a longer client timeout.
curl https://luckyapi.online/v1/images/generations \
--max-time 240 \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-image-2","prompt":"A red apple on a wooden table"}'The current public route supports image generation. Image editing is not listed as a supported endpoint.
Anthropic Messages
Claude
POST /v1/messagesUse the native Anthropic Messages request shape with Bearer authentication.
curl https://luckyapi.online/v1/messages \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-H "anthropic-version: 2023-06-01" \
-d '{"model":"claude-sonnet-5","max_tokens":1024,"messages":[{"role":"user","content":"Hello!"}]}'Token count: POST /v1/messages/count_tokens
Chat Completions
Kimi
POST /v1/chat/completionsKimi uses its native Chat Completions boundary and the same Bearer key.
curl https://luckyapi.online/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"k3","messages":[{"role":"user","content":"Hello!"}]}'Model catalog: GET /v1/kimi/models
xAI Responses
Grok
POST /v1/grok/responsesGrok uses the namespaced Responses endpoint and streams Server-Sent Events.
curl -N https://luckyapi.online/v1/grok/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"grok-4.5","input":"Say hello in one sentence.","stream":true,"store":false}'Model catalog: GET /v1/grok/models
AntiGravity native
Gemini
POST /v1/antigravity/v1internal:streamGenerateContentGemini is exposed through the captured AntiGravity native protocol, not Google's public Gemini API schema.
curl -N https://luckyapi.online/v1/antigravity/v1internal:streamGenerateContent \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model":"gemini-3.6-flash-high",
"requestType":"agent",
"request":{"contents":[{"role":"user","parts":[{"text":"Say hello in one sentence."}]}]}
}'Do not point Gemini CLI or a Google GenAI SDK at this endpoint; their public protocol is different.
Models & Pricing
Model
Provider
Input
Cache read
Cache write
Output
No matching models.
Privacy Policy
Effective: July 24, 2026
This policy explains how LuckyAPI handles information while providing accounts, API access, usage, and billing features.
Information we process
We process account email, display name, the stable account identifier supplied by Google, session and security metadata, and usage, billing, and payment-status records.
Google sign-in
Google is used only to verify identity. LuckyAPI requests openid, email, and profile scopes, does not request offline access, and does not retain Google OAuth access or refresh tokens.
How information is used
Information is used to create and protect accounts, issue local sessions, provide API service, record usage, settle charges, prevent abuse, and meet necessary security and legal obligations.
Sharing and retention
We do not sell personal information. Information is processed only as needed for hosting, payment, security, or legal compliance, and retained only for operational, security, accounting, and legal needs.
Your choices
You may stop using Google sign-in. To request access, correction, or deletion of account data, use the contact channel through which your LuckyAPI access was provided.
Terms of Service
Effective: July 24, 2026
By using LuckyAPI, you agree to these service terms.
Accounts and credentials
Provide accurate account information and protect sessions, passwords, and API keys. Accounts and keys may not be sold, leased, or used for unauthorized access.
Acceptable use
Do not use the service unlawfully, infringe rights, bypass access controls, attack systems, distribute malware, or interfere with other users or upstream services.
Usage and billing
Billing is based on LuckyAPI records of requests, tokens, models, rates, and applicable multipliers. Top-ups, refunds, and payment status follow verified payment results and the rules shown in the product.
Availability
Upstream models and networks can change or fail. LuckyAPI may limit or suspend access for security, compliance, maintenance, or abuse risk, while making reasonable efforts to keep records accurate and service available.
Changes
Material changes update the effective date on this page. Continued use after a change means acceptance of the updated terms.