Proxy Interface

This page is aligned with the current proxy implementation and covers model routes plus dashboard query routes.

Base Information

Base URL: https://api.xaicontrol.com
Auth: Authorization: Bearer sk-Xvs...

export BASE_URL="https://api.xaicontrol.com"

curl ${BASE_URL}/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-4o-mini","messages":[{"role":"user","content":"hi"}]}'

Compatible Proxy Endpoints

OpenAI-compatible

/v1/chat/completions
/v2/chat/completions
/chat/completions
/v1/responses
/responses
/v1/embeddings
/embeddings
/v1/images/generations
/v1/images/edits
/v1/images/variations
/v1/audio/transcriptions
/v1/audio/translations
/v1/realtime/client_secrets
/v1/realtime (WebSocket)
/v1/moderations
/v1/threads
/v1/files
/v1/models, /models

Claude-compatible

/v1/messages
/messages

Dashboard Query Endpoints (same domain, GET)

/dashboard/status
/dashboard/info
/dashboard/live
/dashboard/bill
/dashboard/logs
/dashboard/news
/dashboard/models

Routing Behavior

1) Model mapping

Model names are resolved using:

user-level ModelMapper
owner-level ModelMapper

2) Level routing

LevelMapper chooses the key-pool level, then keys are selected by round-robin.

3) Failover

Two layers are supported:

ModelFailover (model chain)
SwitchOver (level switch)

4) ACL and limits

Requests are checked against:

IP allowlist (AllowIPs)
resource allowlist (Resources)
model allowlist (AllowModels)
user/model rate limits (ModelLimits)