Gemini 3.1 Pro
Google · Gemini · measured on live video
Overshoot API id gemini-3.1-pro-preview
ClosedReasoningImage + Video
- Rank
- #3of 13
- Intelligence
- 83
- Speed
- 106 tok/s
- TTFT
- 125 ms
- E2E
- 7.6 s
- Blended $/1M
- $5.83
- Params
- –
- Context
- 2M
- License
- Proprietary
- Released
- Jan 2026
Speed, TTFT, E2E, and price at Google Vertex, US East (Virginia) reference region. Rank is position on the VLM Intelligence Index.
Capability breakdown
Intelligence over time
Provider & region options
Fastest loop: Google Vertex · US East (Virginia) · 7.6 s end to end.
| Google Vertex | US East (Virginia) | 106 tok/s | 125 ms | 7.6 s | $5.83 | – |
| Google Vertex | US West (Oregon) | 106 tok/s | 133 ms | 7.6 s | $5.83 | – |
| Google Vertex | EU West (Ireland) | 106 tok/s | 148 ms | 7.6 s | $5.83 | – |
| Google Vertex | Asia Pacific (Tokyo) | 106 tok/s | 163 ms | 7.6 s | $5.83 | – |
| Google Vertex | Asia Pacific (Mumbai) | 106 tok/s | 175 ms | 7.6 s | $5.83 | – |
| Overshoot | US East (Virginia) | 99 tok/s | 85 ms | 8.4 s | $5.90 | – |
| Overshoot | US West (Oregon) | 99 tok/s | 98 ms | 8.4 s | $5.90 | – |
| Overshoot | EU West (Ireland) | 99 tok/s | 105 ms | 8.4 s | $5.90 | – |
| Overshoot | EU Central (Frankfurt) | 99 tok/s | 117 ms | 8.4 s | $5.90 | – |
| Overshoot | Asia Pacific (Tokyo) | 99 tok/s | 129 ms | 8.5 s | $5.90 | – |
| Overshoot | Asia Pacific (Mumbai) | 99 tok/s | 142 ms | 8.5 s | $5.90 | – |
| Overshoot | Middle East (Dubai) | 99 tok/s | 149 ms | 8.5 s | $5.90 | – |
| Overshoot | South America (São Paulo) | 99 tok/s | 157 ms | 8.5 s | $5.90 | – |
Sample outputs
Illustrative samples shared across models, not verbatim output from Gemini 3.1 Pro.
“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
- #2GPT-5.485.4
- #3Claude Sonnet 4.682.7
- #3Gemini 3.1 Pro82.7
- #5Qwen3.6 35B A3B80.9
- #6Qwen3.6 27B77.0
- #7GPT-5.4 mini75.5