Blog compares OpenAI Realtime and GPT-Live voice billing models
11/07/2026 — 11/07, 16:18·1 sources (all)·1 reports (all)
Key takeaways
- A blog post breaks down the metering differences between OpenAI's Realtime and GPT-Live voice interfaces: Realtime bills input and output to…
Background & analysis
On November 7, 2026, a Juejin post titled "How OpenAI Realtime and GPT-Live speech billing logic differs" relayed a blog post that dissects the metering logic of two OpenAI voice interfaces.
According to the article, the blog explains that the two products bill differently: OpenAI Realtime is billed per input and output token in a Response, with cache tokens broken out separately, while GPT-Live is billed by the second of active session time. The author accordingly cautions that speech-transcription minutes should not be used as a direct estimate of the cost of a voice conversation.
With only this single report available, additional context, responses from either party, and any independent verification of the claim cannot yet be confirmed. Further reporting is needed to establish how widely the distinction applies in practice.
AI-generated from 1 reports · updated 9 hours ago
- Heat index
- 76
- All sources
- 1
- All reports
- 1
- First seen
- 9 hours ago
Reports on this story headlines open the original
A blog post breaks down how OpenAI's Realtime and GPT-Live voice APIs meter usage: Realtime bills input and output tokens per response with separate cache accounting, while GPT-Live charges by active session seconds. That means transcription minutes are not a valid proxy for estimating voice conversation cost.
掘金AI score 53
Other stories people are talking about
- Heat index 755OpenAI closes $11B tranche at $1.25T valuation, down from a $30B plan12 sources
- Heat index 711Anthropic IPO valuation expectations fall to $1.1 trillion amid AI selloff14 sources
- Heat index 509Meta adds Spaces and a new model to Muse in the US11 sources
- Heat index 483Thinking Machines Lab releases Inkling 2 Small amid reported $5B funding round12 sources
- Heat index 366Gemini Omni 1.2 Flash is now available via Gemini API, Google AI Studio and Google Cloud, generating native 15-second audio-video clips at $0.07 per second.10 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion