Model mapping
X420 model map
The exact model IDs a developer can put in an OpenAI-compatible SDK request.
Use the public ID in your request
X420 keeps a stable public model ID for your app, then resolves the upstream alias server-side. Your code stores the X420 key and the public model ID only.
| Public model ID | Upstream alias | SDK value | Status | Billing |
|---|---|---|---|---|
openai/gpt-5.5 | gpt-5.5 | openai/gpt-5.5 | Active | X420 credit + per-key spending cap |
Rules for developers
- Use public_model_id as the model value in /v1/chat/completions.
- Call GET /v1/model-map before deploy if you want a runtime guard.
- Set allowed models on each X420 key when one app should be locked to one model.
- Provider credentials and route choice stay server-side. Never ship upstream secrets to clients.
Runtime endpoint
curl https://api.x420.ai/v1/model-map
Request example
curl https://api.x420.ai/v1/chat/completions \
-H "Authorization: Bearer $X420_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-5.5",
"messages": [{"role": "user", "content": "Give me a concise launch checklist."}],
"max_tokens": 700
}'