Tokens interpretation (OpenAI)

Dear Community!

Currently testing Chat-gpt 3.5 turbo (OpenAI) and there are so many questions rising....

How are tokens calculated? I need to assess approximate costs, but something is definitely wrong:

Example: 

I have performed a pretranslation of 2549 words; 36829 tokens were counted, corresponding to (x4) 147316 characters....while the entire text had 14230 characters....how come?

Ok, the numbers are always doubled since it´s not only the origin (output) text that is counted, but the input as well. But then it could be around 4000 tokens (30000 characters) tokens, not 37 000 tokens (147 000 characters)...

Completely lost ...and then, in the breakdown, the OpenAI account shows 5 times higher input than output....

For this test I have not activated neither the terminology-aware, nor the multiple-translation options. I guess these may lead to a considerable increase of the input tokens...Would they?

If someone controls the issue, please, clarify.

It is obvious that exact token calculation and estimation is not possible. But at least, the numbers should be more o less clear...

Thank you in advance!



Removed AI Suggestion
[edited by: Yulia Kovalskaya at 4:19 PM (GMT 0) on 29 Oct 2025]
emoji
  •   I really like it! I personally never thought much about the token count because I knew enough about the way such prompts are engineered, but I find it very interesting to be able to see the complete messages to better understand what exactly happens.

    I believe that your tool will become even more important the more direct API calls are made from Trados Studio itself or whatever plugin is using LLMs in the future.

    Another curious coder question (if I may): Which kind of licensing and registering system did you use for this app?

    emoji
  • BTW, one small detail ... I would change the following German translations:

    Überwachung start -> Überwachung starten (even better: Überwachung beginnen)

    Überwachung stopt -> Überwachung stoppen (even better: Überwachung beenden)

    emoji
  •  

    Another curious coder question (if I may): Which kind of licensing and registering system did you use for this app?

    Good question... I actually built my own.  In the spirit of being able to do so much with AI I extended that principle into my Wordpress installation and built several plugins that allow me to do many things I wanted without having to pay for them :-)

    So the licensing is there for two reasons:

    1. I was interested to see if I could create a reasonably secure licence without the need for server checks that recognised the user in the about box as you will have seen.
    2. the reason for the recognition is that's how I wanted to control support.  I also have a support platform (just a simple one) in my Wordpress platform and I'll support questions from licensed users on my apps.

    In reality, it's a bit of fun, I learned a lot... and in practice I think it works quite well.

    Überwachung start -> Überwachung starten (even better: Überwachung beginnen)

    Überwachung stopt -> Überwachung stoppen (even better: Überwachung beenden)

    Thank you for that... will be in the next release :-)

    Paul Filkin | RWS Group

    ________________________
    Design your own training!

    You've done the courses and still need to go a little further, or still not clear? 
    Tell us what you need in our Community Solutions Hub

    emoji
  •  

    Thanks for sharing! I think that licensing system is quite cool.:-)

    I build most of my own websites (and client websites together with some colleagues) nowadays with the CMS Statamic in Laravel, as I’m a fan of that framework. I’m moving away from WordPress (felt mostly too limited there and the bunch of plugins overwhelming) and also enjoy the increased power I get by leveraging AI and AI agents (mostly using Windsurf in PhpStorm and as a standalone editor, mainly with Claude 4.5).

    Do you think we will see more and increased usage of LLMs in Trados Studio and/or plugins soon? And more grades of freedom re. model choice and prompt engineering?

    emoji
  •  

    I build most of my own websites (and client websites together with some colleagues) nowadays with the CMS Statamic in Laravel

    Looks pretty interesting.  I've had a wordpress platform for my blog for over a decade now and transitioned from Wordpress to a hosted version where I have more control, so I'll stick with that for my own needs for now.  The number of plugins is overwhelming and you rarely get exactly what you need... or you get far too much and it's bloat and advertising.  So I started using Code Snippets to bend them and eventually realised it was simpler to build your own complete plugin and I've slowly but surely been replacing the ones I had with my own plugins to do only what I need.

    Do you think we will see more and increased usage of LLMs in Trados Studio and/or plugins soon? And more grades of freedom re. model choice and prompt engineering?

    I think it’s important to separate what Trados Studio itself is responsible for from the level of freedom you’re looking for.  Studio is used by very large enterprises as well as individual freelancers, so anything built into the core product has to meet strict requirements around governance, consistency, data protection and long-term support.  That naturally limits how much unconstrained model choice or prompt experimentation we can expose directly in the out-of-the-box features.

    However, this doesn’t mean there’s no flexibility.  Our aim is to provide a solid, reliable platform while enabling far more freedom through the ecosystem.  Third-party developers can already build plugins that offer broader model selection, custom prompts and specialised workflows, and several of these are available today on the AppStore.  That’s where we see the most room for rapid innovation and experimentation.

    At the same time, we are expanding our own AI capabilities in a more controlled, enterprise-grade way.  Features such as batch Generative Translation, Smart Review, Generative Subtitling, Content Analysis etc. already sit on top of a huge selection of modern LLMs with the right safeguards, and this will continue to evolve.

    So yes - I think LLM usage will increase across Studio and the wider ecosystem.  The difference is simply where freedom sits: core Trados features must remain stable and governed, while plugins and integrations can deliver the flexibility and customisation many users want.

    But  can probably provide a better insight than me.

    Paul Filkin | RWS Group

    ________________________
    Design your own training!

    You've done the courses and still need to go a little further, or still not clear? 
    Tell us what you need in our Community Solutions Hub

    emoji
  •    

    Thank you very much for sharing your views re WordPress. If I had stayed with WP (I'm currently moving my personal website to Statamic), building your own plugins would have been a great idea.

    Your thoughts on the future of AI/LLMs within the Trados ecosystem are very interesting, and you're probably right. I'm happy to check out whatever is offered by RWS, but will probably use my own solution to make initial translation and improving passes.

    emoji