Nufar Gaspar
speaker
2,488 appearances
11 recordings
1 series
first heard Oct 2025
last heard 3 Sep
Nufar Gaspar’s voice in public audio — every appearance, attributed to the second.
Trend
recordings per month · last 12 monthsRecordings per month over the last 12 months — 11 in all, peaking in Jun 2026 with 5.
Appearances
If you look at the Fable 5, it's about $10 per million input tokens and $50 per million with the GPT 5.6 solids 6x ratio.
So we're seeing the gap even widening.
And those effort levels, that's also something that highly adds the complexity because these
Frontier models increasingly letting you dial the reasoning effort.
With higher efforts, the reasoning tokens are significantly higher.
And that's probably the dial that you should even be more mindful of, even beyond the models, because those can easily cost you 10 to 12x token increase between high or extra high effort to the low or medium effort.
All right.
One last thing here, price tag that experiment that came from Databricks, because a smarter model might not always be more expensive than a less expensive model.
What Databricks did is they tested coding agents on real engineering tasks from its own code base, and they were using Sonnet 5.
It was 1.7 times cheaper per token than Opus 4.8.
However, Sonnet cost around $2 per task or $2.09 per task versus $1.94 for Opus.
So because Sonnet needed more iterations and more reasoning, had to spend way more tokens to get to the same results, overall, Opus, which is significantly on paper more expensive model, it was cheaper to operate, which means that we shouldn't just reach to the cheapest model possible.
We need to reach to the right model
for the task, and that's not easy to get, but something to be mindful.
The other thing that matters to the bill is the tool itself.
So Databricks, in their same experiment, ran the same model at the same thinking effort through different agent harnesses, and they saw that more than a 2x difference in cost per task with the same quality using different harnesses, just because primarily one tool was feeding the model roughly three times less context than the others, and thereby the overall cost was lower.
So very difficult build to read and very difficult build to navigate and I'll try to help you as best I can.
So bottom line, we're dealing with cost per task and not tokens because otherwise we will not be able to actually compare apples to apples and the
The cost will include the rate rise, the review, every correction that needs and every additional iteration.
And then you need to divide by the number of accepted results.
Showing 781–800 of 2,488 · page 40 of 125
← Previous
Next →