The detail parameter controls image resolution and directly affects token cost.
| Level | Description | Token Cost (gpt-4o) |
|---|---|---|
low | Resized to 512×512, fixed cost | ~85 tokens |
high | Full resolution, tiled analysis | ~765 tokens (1024×1024) |
auto | Model decides based on content | Varies |
Token Cost Calculation (high detail)
For gpt-4o, gpt-4.1, gpt-5 (tile-based):
- Scale image to fit within 2048×2048
- Resize shortest side to 768px
- Count 512px tiles: tiles × 170 tokens + 85 base tokens
| Model Family | Base Tokens | Per Tile |
|---|---|---|
| gpt-5, gpt-5-chat | 70 | 140 |
| gpt-4o, gpt-4.1 | 85 | 170 |
| o1, o3 | 75 | 150 |
Example: A 1024×1024 image with high detail on gpt-4o = 4 tiles × 170 + 85 = 765 tokens. The same image with low = 85 tokens. Use low when fine detail isn't needed.