Capability breakdown
Intelligence over time
Provider & region options
Fastest loop: Overshoot · US East (Virginia) · 1.4 s end to end.
| Overshoot | US East (Virginia) | 354 tok/s | 28 ms | 1.4 s | $3.20 | – |
| Overshoot | US West (Oregon) | 354 tok/s | 44 ms | 1.4 s | $3.20 | – |
| Overshoot | EU West (Ireland) | 354 tok/s | 47 ms | 1.4 s | $3.20 | – |
| Overshoot | EU Central (Frankfurt) | 354 tok/s | 61 ms | 1.5 s | $3.20 | – |
| Overshoot | Asia Pacific (Tokyo) | 354 tok/s | 64 ms | 1.5 s | $3.20 | – |
| Overshoot | Asia Pacific (Mumbai) | 354 tok/s | 85 ms | 1.5 s | $3.20 | – |
| Overshoot | Middle East (Dubai) | 354 tok/s | 90 ms | 1.5 s | $3.20 | – |
| Overshoot | South America (São Paulo) | 354 tok/s | 97 ms | 1.5 s | $3.20 | – |
| OpenAI API | US East (Virginia) | 354 tok/s | 48 ms | 1.7 s | $3.20 | – |
| OpenAI API | US West (Oregon) | 354 tok/s | 53 ms | 1.7 s | $3.20 | – |
| OpenAI API | EU West (Ireland) | 354 tok/s | 60 ms | 1.7 s | $3.20 | – |
| OpenAI API | Asia Pacific (Tokyo) | 354 tok/s | 85 ms | 1.7 s | $3.20 | – |
Sample outputs
Illustrative samples shared across models, not verbatim output from GPT-5.4 nano.
Scene description
“Describe what's happening in this camera frame.”
A forklift is reversing toward loading bay 3 while a worker in a hi-vis vest signals from the left. Two pallets remain unwrapped near the dock edge.
OCR + extraction
“Read the shipping label and return structured JSON.”
{ "tracking": "1Z A24 9W7 03 8421 990 4", "carrier": "UPS", "weight_kg": 12.4, "dest": "Portland, OR 97204" }
Grounding
“Point to every person not wearing a hard hat.”
2 detections, [x:0.41, y:0.62, w:0.08, h:0.19] conf 0.94 · [x:0.77, y:0.55, w:0.07, h:0.21] conf 0.88.
Related models
Where it ranks
- #8Gemini 3 Flash75.3
- #9Claude Haiku 4.574.2
- #10Holo3 35B A3B74.0
- #11Gemma 4 31B73.0
- #12Gemma 4 26B A4B69.3
- #13GPT-5.4 nano63.6