GPT-5.4
OpenAI · GPT · measured on live video
Overshoot API id gpt-5.4
ClosedReasoningImage + Video
- Rank
- #2of 13
- Intelligence
- 85
- Speed
- 91 tok/s
- TTFT
- 138 ms
- E2E
- 9.3 s
- Blended $/1M
- $6.68
- Params
- –
- Context
- 400k
- License
- Proprietary
- Released
- Mar 2026
Speed, TTFT, E2E, and price at OpenAI API, US East (Virginia) reference region. Rank is position on the VLM Intelligence Index.
Capability breakdown
Intelligence over time
Provider & region options
Fastest loop: Overshoot · US East (Virginia) · 8.9 s end to end.
| Overshoot | US East (Virginia) | 96 tok/s | 87 ms | 8.9 s | $6.63 | – |
| Overshoot | US West (Oregon) | 96 tok/s | 101 ms | 8.9 s | $6.63 | – |
| Overshoot | EU West (Ireland) | 96 tok/s | 103 ms | 8.9 s | $6.63 | – |
| Overshoot | EU Central (Frankfurt) | 96 tok/s | 117 ms | 9.0 s | $6.63 | – |
| Overshoot | Asia Pacific (Tokyo) | 96 tok/s | 129 ms | 9.0 s | $6.63 | – |
| Overshoot | Asia Pacific (Mumbai) | 96 tok/s | 137 ms | 9.0 s | $6.63 | – |
| Overshoot | Middle East (Dubai) | 96 tok/s | 141 ms | 9.0 s | $6.63 | – |
| Overshoot | South America (São Paulo) | 96 tok/s | 157 ms | 9.0 s | $6.63 | – |
| OpenAI API | US West (Oregon) | 91 tok/s | 137 ms | 9.3 s | $6.68 | – |
| OpenAI API | US East (Virginia) | 91 tok/s | 138 ms | 9.3 s | $6.68 | – |
| OpenAI API | EU West (Ireland) | 91 tok/s | 154 ms | 9.3 s | $6.68 | – |
| OpenAI API | Asia Pacific (Tokyo) | 91 tok/s | 172 ms | 9.3 s | $6.68 | – |
Sample outputs
Illustrative samples shared across models, not verbatim output from GPT-5.4.
“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.
“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" }
“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
- #1Claude Opus 4.685.7
- #2GPT-5.485.4
- #3Claude Sonnet 4.682.7
- #3Gemini 3.1 Pro82.7
- #5Qwen3.6 35B A3B80.9
- #6Qwen3.6 27B77.0