Hacker News Reader

Comment by bsboxe | Hacker News Reader

The input and output pricing per token remains the same between 2.5 and 2.6, although using their image pricing calculator shows a quadrupling of token usage at low and medium quality settings for 2.6. For e.g. at 1024x1024:

2.5 low, 196 tokens, $0.006

2.6 low, 823 tokens, $0.025

2.5 med, 439 tokens, $0.013

2.6 med, 1449 tokens, $0.043

Interestingly, higher quality settings show no change in token usage between the models.

View on HN

Similar results for my workflow. And the Round art comes out significantly less round without prompt changes (more input tokens)

  Setting (1024x1024)   Tokens   Cost/image   Time
  2.5 medium              439     $0.014     12.0 s
  2.6 low                 824     $0.025      6.7 s
  2.6 medium            1,449     $0.044      7.9 s
  2.6 high              1,758     $0.053      8.9 s

same in my testing; super deceptive marketing here. it’s 3-4x the true cost of 2.5.

Output image tokens per image (2.5 Flare → 2.6 Flare / Sunburst)

low, 1024x1024: 196 → 824 (4.2x) medium, 1024x1024: 439 → 1,449 (3.3x) low, 1024x1536: 158 → 664 (4.2x) medium, 1024x1536: 343 → 1,132 (3.3x)

Same $30/1M output tokens on all three, so per image: low: $0.006 → $0.025 medium: $0.013 → $0.043

Same results here, seems like a hidden price increase, hopefully they will still keep 2.5 running for some time.

from 800 to 1500 is barely 2.

from 200 to 450 is just a little over 2.

Nothing near "quadrupling"

196 tokens with 2.5 to 823 tokens with 2.6 is more than quadrupling.

439 tokens with 2.5 to 1449 tokens with 2.6 is 3.3 times.

I’m talking about low quality 2.5->2.6 and medium quality 2.5->2.6, not low vs medium in the same version number.

Reply on news.ycombinator.com