I’ve read through the few posts here about the pricing challenges with Realtime API. I am going to share my observation in helping us all understand what’s really going on. Starting Point: Tokens are accumulated and “carried forward” which has an inflationary impact on total tokens consumed per…

A simple fix is to just limit the number of turns of conversation history you maintain. You should be able to prune to the last 3 turns and still have linguistic features like co-reference work. The default output token count they use in their examples is 2k tokens which is a lot. That may seem kin…

in that case you’d still need to do your own transcription to pull any rag references (since you can’t store it in the context) and even then I don’t think you can come to any sort of cost parity to a human who meets or exceeds 4o intelligence.

[image] Diet: and even then I don’t think you can come to any sort of cost parity to a human who meets or exceeds 4o intelligence. This is for: Startups that have participated in OpenAI’s programs so they get VC stakes for their funding, where you are the partners seen in announcements who …

I understand the point you’re trying to make with regards to “trimming” the context. But what about this: Each audio input/output is being transcribed anyway. So what’s the point of retaining the audio tokens once they have been transcribed? Why not delete the audio event_id and retain the transcri…

So that’s it? Another case of “started with: Do no evil” but ended up in “Alphabet” soup?

That’s just the impression I get - that there is another customer they are going for instead of those that would visit the forum or be on the payment tier system. Ones that can either afford this or ones that don’t even get this pricing. Or the ultimate customer is those that would sign up for ChatG…

[image] liquidshadowsmk: Each audio input/output is being transcribed anyway. So what’s the point of retaining the audio tokens once they have been transcribed? Why not delete the audio event_id and retain the transcription which goes toward text tokens (much cheaper). The transcription isn’t…

So then… perhaps maintain a dictionary of all audio events, retain the last 3 (or 5) and delete the rest to somewhat reduce the carry-forward load? I guess, in a long conversation (>5 mins with at least 10 exchanges) there’s no way to reach the $0.06/min input and $0.24/min output cost range as sti…

This is an encouraging response from OpenAI Staff: Thank you @jeffsharris [image] Realtime API pricing is wrong, will overcharge I’d love your org info if you’re seeing problems here (feel free to DM me) One debug step that’s helpful to check is using the Playground , you can see the total toke…

I don’t really think that the mechanics of the API are the major issue for cost. The major issue is the cost $.24 per minute that’s just way way too much. I can get high resolution video streams with audio for that.

Realtime API Pricing: VAD and Token Accumulation - A KILLER

Community

liquidshadowsmk October 16, 2024, 3:13am 12

This is an encouraging response from OpenAI Staff:

Thank you @jeffsharris

Topic		Replies	Views
New Realtime API voices and cache pricing Announcements realtime , prompt-caching	26	13342	September 2, 2025
Realtime API extremely expensive Feedback realtime	66	9046	December 4, 2024
What does "auto" truncation in realtime api actually do? Documentation gpt-realtime	6	1036	November 28, 2025
Realtime API pricing questions: text input and audio tokens API realtime	7	873	December 6, 2025
Realtime API pricing is wrong, will overcharge API realtime	36	5226	January 15, 2025

Realtime API Pricing: VAD and Token Accumulation - A KILLER

Related topics