AI gateway
Same model. Shorter trip.
Every major model, behind one OpenAI-compatible endpoint. Switch regions to watch the network cost change — the model's thinking time stays the same wherever you call it from, so the round trip is the part proximity actually buys.
No result from Colombo yet. Send the prompt here, then switch regions and send it again — each region keeps its own numbers so you can compare them.
Colombo · this request
- gateway round trip (warm)
- –– ms
- time to first token
- –– ms
- total time
- –– ms
- ≈ tokens / second
- ––
Gateway round trip is the network cost of reaching this region — that is what proximity buys you. Time to first token adds the model's own thinking time, which is the same wherever you connect from.