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
https://api.luckyapi.online
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://api.luckyapi.online/v1- Claude Code
https://api.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 = "luckyapi"
[model_providers.luckyapi]
name = "LuckyAPI"
base_url = "https://api.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://api.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://api.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://api.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.
OpenAI SDK
Chat Completions
POST /v1/chat/completionsCall the OpenAI Chat Completions contract with the official OpenAI SDK.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.luckyapi.online/v1",
)
result = client.chat.completions.create(
model="gpt-5.5",
messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(result.choices[0].message.content)OpenAI SDK
Responses
POST /v1/responsesCall the OpenAI Responses contract with the official OpenAI SDK.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.luckyapi.online/v1",
)
result = client.responses.create(
model="gpt-5.6-sol",
input="Say hello in one sentence.",
)
print(result.output_text)Model catalog: GET /v1/models
Anthropic SDK
Messages
POST /v1/messagesCall the Anthropic Messages contract with the official Anthropic SDK.
from anthropic import Anthropic
client = Anthropic(
api_key="YOUR_API_KEY",
base_url="https://api.luckyapi.online",
)
result = client.messages.create(
model="claude-sonnet-5",
max_tokens=1024,
messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(result.content[0].text)Token count: POST /v1/messages/count_tokens
OpenAI Images
GPT Image
POST /v1/images/generationsImage generation can take longer than text requests, so allow a longer client timeout.
curl https://api.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.
xAI Responses
Grok
POST /v1/grok/responsesGrok uses the namespaced Responses endpoint and streams Server-Sent Events.
curl -N https://api.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
Managed Video
Grok Video
POST /v1/grok-web/videos/generationsRun one script to generate the video, read the terminal event, and download the MP4.
(
set -euo pipefail
API_KEY="YOUR_API_KEY"
RESULT_FILE="$(mktemp)"
OUTPUT_FILE="./grok-video-$(date +%Y%m%d-%H%M%S).mp4"
trap 'rm -f "$RESULT_FILE"' EXIT
curl -N -sS --fail-with-body --max-time 900 \
"https://api.luckyapi.online/v1/grok-web/videos/generations" \
-H "Authorization: Bearer ${API_KEY}" \
-H "Content-Type: application/json" \
-d '{
"prompt":"A paper airplane flying through a sunlit library",
"aspect_ratio":"16:9",
"duration":6,
"resolution":"720p"
}' | tee "$RESULT_FILE"
VIDEO_URL="$(
jq -r '
select(.result.response.streamingVideoGenerationResponse.progress == 100)
| .result.response.streamingVideoGenerationResponse.videoUrl // empty
' "$RESULT_FILE" | tail -1
)"
if [ -z "$VIDEO_URL" ]; then
echo "Generation finished without a video URL." >&2
exit 1
fi
curl -L --fail --progress-bar "$VIDEO_URL" -o "$OUTPUT_FILE"
echo "Saved: $OUTPUT_FILE"
)Requires curl and jq. Aspect ratio: 2:3, 3:2, 1:1, 9:16, or 16:9. Duration: 6, 10, or 15 seconds. Resolution: 720p. The script downloads the MP4 after progress reaches 100; asset URLs expire after one hour.
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://api.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.
PARTNERSHIPS
Partner with LuckyAPI
Project Sponsorship
Token sponsorship for quality projects, helping them reach more users.
Channel Revenue Share
A 30% token revenue share for quality software and agents: integrate our tokens into your product and earn on every user's usage.
Reach us through the channel where you received LuckyAPI access.
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 and username, session and security metadata, and usage, billing, and payment-status records.
Account identity
Account identity and credentials are processed to authenticate you, protect access, and recover your account.
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
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.