Trying the new o3-deep-research model through the Responses API. 1m tokens spent (see screen shot) - no output. If anyone at OpenAI wants to take a look: resp_685fdd88e168819ab808c4f49f7b112102dea5e6d8d627d0 There is no actual ‘response’ No tools other than websearch (which according to the log …

I love you guys so much, I work for cheap

Its mainly because all development and production apps using the API are metered, unlike ChatGPT

In general the growth of our internal token usage over time is making me realize that there is no upper limit for this kind of stuff. It will continue to grow. But I can also see that for stuff like deep research good prompting and guard rails are just as important or even more. Because now you get…

I mainly use API not ChatGPT for anything important… Spent WAY MORE on ChatGPT than API It really is about asking the right questions ^^. And for us ‘cheaps’… At the right time (Best results still from API but maybe the questions I ask there)

I have three live websites using the API. They are tightly and periodically optimised but still cost $. There’s no way around that.

Yeah I’m a selfish nub who doesn’t run websites and just relays my knowledge locally (kinda weird I know)… I used to build websites… Is that still where the world is going?

[image] jlvanhulst: Because now you get back pages of results that cannot be easily validated anymore. They should have sources, no?

[image] phyde1001: I used to build websites… Is that still where the world is going? This is a website (and PWA) … so yeah, I think websites are as relevant as ever. If anything I think apps are becoming less relevant and redundant. A lot of apps are just wrapped websites these days. (t…

[image] merefield: (this is super off topic now so very happy if these posts are moved) Oooh… ‘Wasted thought’ I think it’s still on topic :smiley: I am not thinking apps… Apps? I only think people. No disrespect… I know how hard websites are… But this is not the mission statement of Open…

O3-deep-research - 1 million tokens spent .. no output :(

API

jlvanhulst June 28, 2025, 7:04pm 28

Sure but there is no easy ‘evals’ to run on a 10 page report. You can of course let an AI read it

Why are Deep Research API token counts so high?

Topic		Replies	Views
Infinite wait for OpenAI server response with GPT5 on /completions under specific conditions API gpt5	13	1403	January 12, 2026
What is going on with the GPT-5 API? API	40	18539	October 21, 2025
Frequent errors when using o3-deep-research Bugs	1	325	September 2, 2025
Why are Deep Research API token counts so high? Feedback deep-research	7	1162	August 21, 2025
Test new 128k window on gpt-4-1106-preview API	28	19040	November 19, 2023

O3-deep-research - 1 million tokens spent .. no output :(

Related topics