01
Minimal migration
Replace the Base URL and API key. Keep the same OpenAI-style request body.
base_urlapi.gpt88.cc/v1
authBearer sk-••••
formatOpenAI JSON
Unified API Gateway · OpenAI Compatible
One base_url for all models on gpt88.cc
Use GPT, Claude, Gemini, DeepSeek, Qwen, image models, and more through one OpenAI-compatible API. Replace the Base URL and API key, then keep your existing SDK.
Text & agentsImage & videoOpenAI Compatible
POST /v1/chat/completionsLive routing
curl https://api.gpt88.cc/v1/chat/completions \
-H "Authorization: Bearer $GPT88_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-4.6",
"messages": [{"role": "user", "content": "Hello GPT88"}]
}'01
Minimal migration
02
One gateway, many models
03
Usage-based billing
API architecture
One integration, two endpoints
Use the unified OpenAI-compatible endpoint for standard models and the media endpoint for image and video workloads.
Developer workflow
Built around real workflows
Move from the first request to production troubleshooting with direct, usable entry points.
02
One gateway, many models
Switch between chat, image, video, and audio models with a consistent integration path.
03
Usage-based billing
See actual usage and account balance clearly. No opaque virtual-points conversion.
Model catalog
Change models, not integrations
Keep one authentication and request format while choosing the right capability from the model catalog.
ModelsObservability
Status
99.94%
Latency
842ms
Route
03 / 05
route-0182%
route-0264%
route-0391%
route-0447%
Request ledger
Every request stays observable
Status, routing result, latency, and usage remain attached to the same request record.
Activation paths
Get Started
Make your first gpt88.cc API request in 5 minutes by replacing only the Base URL and API key.
GPT88 / API
Ready to send your first request?
Create an API key, copy the endpoint, and call it from your existing OpenAI-compatible SDK.