OpenAI-compatible·23 models·4 providers

One gateway for every LLM

Issue API tokens, enforce rate limits, meter credits, and watch real-time analytics. Point any OpenAI SDK at our endpoint and go.

Create free accountView status
quickstart — curl
curl https://your-gateway.com/v1/chat/completions \
  -H "Authorization: Bearer sk-gw-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role":"user","content":"Hello!"}]
  }'
23
Models available
4
Upstream providers

Everything you need to ship

Token generation

Issue and revoke scoped API keys. Hashed at rest, shown once.

Rate limits

Per-key RPM/TPM and daily quotas enforced at the edge with Redis.

Credits & billing

Per-model token pricing, live balance, and a full ledger.

Analytics

Requests, tokens, cost, latency, and error rates over time.

Status page

Upstream provider health, uptime, and incident history.

Admin panel

Manage users, keys, pricing, tiers, and global usage.