Skip to content
TEN Brief Ten verified stories a day 2026.11.21 KO

이 기사는 한국어로도 읽을 수 있습니다 →

Tech · 15 min read · Explainer

GPT-Live-1.1 API pricing — $0.05 a minute, $0.02 on standby

GPT-Live-1.1 API pricing is 0.05 dollars per minute of active session time and 0.02 dollars per minute on standby. OpenAI made the voice model available to developers on November 19, 2026 (US time) under the model ID gpt-live-1.1 at the v1/live/sessions endpoint. Voice sessions are billed by duration, not by token. The standby rate applies only to WebRTC sessions while inference is paused, and silence alone does not trigger it. The backend model that handles reasoning and tool calls behind the voice is billed separately at its own rates. Structured outputs, fine-tuning and image input are not supported. The voice catalog, the list of supported languages, latency figures and concurrency limits for 1.1 have not been published.

A developer seen from behind wearing a headset and testing a voice app on a laptop in a sunlit studio workspace at midday

The three lines

  • Price — $0.05 per active minute ($3 an hour) and $0.02 per standby minute ($1.20 an hour), per the OpenAI model page. Billing is by session duration; per-second billing is stated by two secondary sources
  • Conditions — standby applies to WebRTC sessions while inference is paused. Without an idle timeout the session stays at the active rate. Backend model and tool usage is billed separately
  • Limits — no structured outputs, fine-tuning or image input. Voices, languages, latency and 1.1 concurrency limits are unpublished. Sources give the API release date as November 19 or November 20, 2026

Key questions

GPT-Live-1.1 API pricing
**$0.05 per minute of active session time and $0.02 per minute on standby. Backend model and tool usage is billed separately.** | Item | Rate | Condition | |---|---|---| | Active session | $0.05 per minute | Session open with inference running | | Standby | $0.02 per minute | WebRTC sessions only, while inference is paused | | Backend model and tools | That model's rates | Separate from the voice session charge | | Per hour | $3.00 active / $1.20 standby | This article's arithmetic |
GPT-Live-1.1 standby pricing how it works
**The session must use WebRTC and inference must be paused. A quiet stretch on its own does not switch the session to the standby rate.** | Condition | Detail | Source | |---|---|---| | Transport | WebRTC | OpenAI model page | | State | Inference paused (session.paused) | Model page, Data Studios | | Setting | session.idle_timeout_s as a whole number from 5 to 60 seconds | Data Studios, DEV Community post | | If omitted | Stays active after the first wake | Data Studios | | WebSocket and SIP | Not addressed on the model page; the DEV post says active rate only | Unsettled |
GPT-Live-1.1 vs GPT-Realtime
**GPT-Live-1.1 is a full-duplex model that listens while it speaks and bills by the minute. GPT-Realtime takes turns and bills by the token.** | Item | GPT-Live-1.1 | gpt-realtime-2.1 | |---|---|---| | Conversation | Simultaneous listening and speaking | Turns detected by voice activity | | Billing | $0.05 per minute ($0.02 standby) | Audio at $32 in / $64 out per 1M tokens | | Architecture | Voice front end that delegates to a backend model | One model hears, reasons and speaks | | Standby rate | Yes (WebRTC) | No | | Image input | Not supported | Listed as supported in the DEV post | The GPT-Realtime figures come from a single DEV Community post.

GPT-Live-1.1 costs $0.05 per minute of active session time in the API, and $0.02 per minute on standby. OpenAI opened the voice model to developers on November 19, 2026 (US time). The model ID is gpt-live-1.1 and the endpoint is v1/live/sessions. The OpenAI model page describes it as a voice model that listens while it speaks, and says voice sessions are billed by duration while backend model and tool usage is billed separately.

Two things will be unfamiliar to developers used to text models. The unit is the minute, not the token. And there are two rates: while a user pauses to think, or a shop kiosk waits for the next customer, a session can drop to a lower standby price. That lower price has conditions. This piece sets out the price table, when standby actually applies, worked costs for different kinds of service, how the model differs from GPT-Realtime, and what OpenAI has not yet published.

1. The price table — $0.05 and $0.02 a minute, plus a backend bill

The table separates what the OpenAI model page states from what secondary sources add.

ItemDetailBasis
Model IDgpt-live-1.1 (the only snapshot, and the default)OpenAI model page
Endpointv1/live/sessions (Live API)Model page, Data Studios
Active session rate$0.05 per minuteModel page and three other sources agree
Standby rate$0.02 per minuteModel page and three other sources agree
Standby conditionWebRTC sessions while inference is pausedModel page
Billing basisSession durationModel page
Per-second billingPer second, no rounding up to the minuteData Studios, DEV Community post
Session startA WebRTC session bills 15 seconds up front, credited against later durationData Studios, DEV Community post
Backend model and toolsBilled separately at that model's normal ratesModel page and three other sources agree
Token, cache and batch discountsDo not apply to the voice session chargeData Studios
ModalitiesAudio and text in, audio and text outModel page

Converted into more familiar units, by this article's arithmetic:

UnitActiveStandbyDifference
1 secondabout $0.00083about $0.00033—
1 minute$0.05$0.0260% lower
1 hour$3.00$1.20$1.80
8 hours$24.00$9.60$14.40
15 seconds at session start$0.0125—Credited against later use

Data Studios, citing OpenAI cost documentation, gives a simple formula: billable voice seconds ÷ 60 × the per-minute rate, plus backend cost. The first half is settled by the tables above. The second half is the harder one to forecast.

GPT-Live-1.1 does not do everything itself. According to the DEV Community post, it is a voice front end that hands reasoning and tool calls to a text model behind it. There are two ways to do that: a responses mode in which OpenAI runs the backend, and a client mode in which the developer's application runs it. The mode cannot change mid-session. Two secondary sources name gpt-6-luna as a starting backend and gpt-6-sol for harder tasks. Those names are not on the model page.

So the invoice has two lines. One scales with how long the call lasted. The other scales with how much thinking the conversation required. A call that exchanges greetings and a call that queries a booking system three times can be the same length and still differ on the second line. In other words, the per-minute figure is a floor on the bill, not the bill.

2. The $0.02 standby rate — silence alone does not earn it

Standby is the headline number of this release, and the easiest to misread. Superpower Daily notes that a quiet stretch does not qualify by itself; the session has to be in the paused state.

Condition or settingDetailBasis
TransportWebRTC sessionModel page
StateWhile inference is pausedModel page
Wake policysession.wake_policy.type set to "speech"Data Studios, DEV post
Idle timeoutsession.idle_timeout_s, a whole number from 5 to 60 secondsData Studios, DEV post
Voice detection thresholdsession.wake_policy.vad_threshold, 0 to 1, default 0.5Data Studios
If the timeout is omittedInference stays active after the first wake and never drops to standbyData Studios
State eventssession.paused and session.resumedData Studios
Connection during standbyConnection and session ID persistData Studios
Muting the microphoneDoes not close the session, so billing continuesData Studios
First response after standbyMay be slower; no figure is givenData Studios

Four points need care.

First, there is no standby unless you configure it. A session with no idle timeout pays $0.05 for every one of the ten minutes a user spends away from the desk. Standby is a feature the developer switches on, not a default.

Second, the timeout itself is billed as active. With a 10-second timeout, the 10 seconds after speech stops are still active time. Six silences mean 60 seconds billed at the active rate. Since the minimum timeout is 5 seconds, every silence costs at least 5 seconds of active time.

Third, mute is not standby. A muted microphone does not close the session or lower the rate. Standby is a server-side session state; mute is a client-side input block.

Fourth, WebSocket and SIP are unsettled. The model page says only that standby applies to WebRTC sessions. The DEV Community post states flatly that WebSocket and SIP sessions bill every connected second at the active rate, which is a stronger claim than the primary source makes. A contact center connecting over the phone network through SIP should confirm with OpenAI documentation before building a budget around standby.

The setting names above match across two secondary sources. Data Studios says its own code snippet is illustrative, not an official sample, and for the same reason this article does not reproduce a full configuration.

3. What your service would cost — worked examples

The first three cases are Data Studios calculations; this article re-checked the arithmetic. All of them cover the voice session charge only. Backend cost is excluded.

CaseSession profileWithout standbyWith standbySaving
30-minute tutoring session (WebRTC)12 minutes of talk, six 3-minute pauses, 10-second timeout$1.50$0.9934%
Shop kiosk, 8-hour shift (WebRTC)480 minutes open: 55 active, 425 standby$24.00$11.25about 53%
Kiosk, 22-day monthThe same shift, 22 times$528.00$247.50about 53%
6-minute support callContinuous conversation$0.30$0.300%

The tutoring arithmetic runs like this. Each of the six pauses leaves a 10-second timeout billed as active, so active time is 12 minutes plus 1, or 13, and standby is 17. Thirteen minutes at $0.05 is $0.65, 17 minutes at $0.02 is $0.34, and the total is $0.99. For the kiosk, 55 × $0.05 = $2.75 plus 425 × $0.02 = $8.50 gives $11.25.

What the cases show is that the value of standby depends entirely on the share of silence. A six-minute call with no gaps saves nothing. A kiosk that waits for most of the day saves more than half. Even the kiosk never reaches zero: an eight-hour shift with no customers at all still costs $9.60 in standby if the session stays open. That may be worth comparing with a design that closes the session when nobody is there and opens a new one on approach. The deciding variables are how slow the first response after standby is and how long a fresh session takes to start. Neither has a published figure.

One larger-scale illustration follows. This is this article's own arithmetic, again excluding backend cost.

AssumptionMonthly volumeVoice charge
One 90-second call1 call$0.075
6-minute calls1,000 calls (6,000 minutes)$300
6-minute calls10,000 calls (60,000 minutes)$3,000
6-minute calls, 2 minutes of each on standby10,000 calls$2,400

The last row assumes four active minutes and two standby minutes per call: 4 × $0.05 + 2 × $0.02 = $0.24, times 10,000. Real calls are messier. Silence comes in many kinds, from a customer hunting for a document to a lookup running in a back-office system, and the timeout eats into every gap. The sensible first step is to measure the distribution of silence lengths in your own call recordings.

The $0.075 figure for a 90-second call comes from the DEV Community post. It holds if the secondary sources are right that billing is per second with no rounding up. That detail was not confirmed against OpenAI text.

4. How it differs from GPT-Realtime — minutes versus tokens

OpenAI now has two voice API tracks. The gpt-realtime-2.1 figures below rest on a single DEV Community post, which should be kept in mind throughout.

ItemGPT-Live-1.1gpt-realtime-2.1
ConversationListens while it speaks (full duplex)Turns detected by voice activity
Barge-inHandled without a settinginterrupt_response setting
ArchitectureVoice front end delegates reasoning and tools to a backendOne model hears, reasons, calls tools and speaks
Billing unitMinutes of session timeTokens
Voice rate$0.05 per minute active, $0.02 standbyAudio at $32 in, $64 out per 1M tokens
Text rateBackend model's rates$4 in, $24 out per 1M tokens
Cached inputNot applicable to the voice session$0.40 per 1M tokens
Standby rateYes (WebRTC)No
Context128,000 tokens per session, managed automatically128,000 tokens, 32,000 max output
Endpointv1/live/sessionsRealtime API

Full duplex is a telecom term for a link on which both sides can talk and listen at once, like a phone call, as opposed to a walkie-talkie where one side speaks at a time. As the DEV post describes it, GPT-Live-1.1 processes incoming audio while it is generating output, so it can offer short acknowledgements and change course mid-sentence. Superpower Daily says the model decides whether to keep listening or answer, instead of following strict turn-taking. The Realtime line waits for voice activity detection to judge that the other party has finished.

A one-line cost comparison is not possible because the units differ. The DEV post works out that $0.05 buys about 1,560 audio input tokens on gpt-realtime-2.1, which is $0.05 divided by $32 per million and checks out. But none of the sources read for this article says how many audio tokens a minute of conversation produces. Without that, nobody can say which is cheaper in general. What can be compared is structure.

Kind of serviceLikely better fitWhy
Long silences, sessions held open for hoursGPT-Live-1.1It has a standby rate; Realtime does not
Costs that must be forecast from call timeGPT-Live-1.1The voice charge scales with time, though backend cost is a separate variable
Responses needed in a fixed schemaCheck firstGPT-Live-1.1 does not support structured outputs
A single-model setup with nothing to wire togetherRealtimeNo backend delegation to configure
Natural acknowledgements and interruptionsGPT-Live-1.1Simultaneous listening and speaking

This table is inferred from the published design, not measured. The only reliable test is to run the same call recordings through both APIs and compare the invoices.

5. What it supports and what it does not

StatusItemBasis
SupportedStreamingModel page
SupportedFunction callingModel page; under responses delegation the tools go in delegation.responses.tools (DEV post)
SupportedAudio and text input and outputModel page
SupportedWebRTC, WebSocket, SIP inbound and outboundDEV post; the model page does not list transports
Not supportedStructured outputsModel page
Not supportedFine-tuningModel page
Not supportedImage inputModel page and three other sources
Not supportedVideo inputSuperpower Daily
Not supportedPredicted outputsData Studios
Unsupported endpointsChat Completions, Responses, Realtime, Batch, Assistants, fine-tuning, audio and image endpointsModel page

Limits that have been stated:

ItemValueBasis
Context128,000 tokens per session, managed automaticallyDEV post
InstructionsUp to 16,384 tokensDEV post
Maximum outputNot publishedDEV post
SIP call lengthTwo hours per connected callDEV post
Other session length limitsNot published—
Concurrent sessionsGPT-Live-1.1 and GPT-Live-1 are counted separately, each across inference regionsModel page
Per-tier limits for 1.1Not published; check the organization limits pageModel page
For reference: GPT-Live-150 on Build, 300 on Launch, 500 on Grow, no Free tierRelayed by secondary sources

The lack of structured outputs matters for business automation. The voice model cannot be asked to return its answer in a fixed JSON schema. Values that need a format, such as a booking reference or an order, have to arrive as function call arguments or be handled by the backend model. Fine-tuning is also unavailable, so tone and business rules have to fit inside the instructions, capped at 16,384 tokens.

As improvements over GPT-Live-1, OpenAI cites more accurate transcription and a more consistent accent and voice across languages. Superpower Daily relays a post from the OpenAI developer account saying 1.1 completes tasks more reliably. None of these claims comes with a number, and no benchmarks have been published. The active rate is the same as the earlier model.

6. What has not been published — voices, languages, latency, limits

This is why the price table alone is not enough to make an adoption decision. Several of the values that determine the quality of a voice product are blank.

ItemStatusWhy it matters
Voice catalogIn no sourceWhether a brand can pick a suitable voice
Supported languagesDescribed only as multilingualNo basis for judging any single language in advance
LatencyNo figuresThe main determinant of whether a conversation feels natural
First response after standbyOnly that it may be slowerThe price paid for the standby discount
Concurrency for 1.1Not publishedConcurrent calls are the capacity of the service
Regional availabilityNo listWhere data is processed, and latency
Session length capNothing beyond the two-hour SIP limitDesign of all-day kiosk sessions
Transcription gainNo figureThe case for migrating from GPT-Live-1
Total cost including backendDepends on model and usageThe actual invoice

For teams building in a language other than English, the missing language list is the largest gap. Whether the model page's word, multilingual, covers a given language, and how well, can only be established by testing. At $0.05 a minute, ten 10-minute test calls cost $5 before backend charges, so the testing itself is cheap.

The safety information is single-sourced. According to Superpower Daily, OpenAI published a system card on October 15, 2026 and added material on the API voice models on November 19. With backend delegation disabled, the 1.1 API is said to score numerically higher than its predecessor on mental health, emotional reliance and self-harm tests, and at parity on sexual content, illicit behavior and personal data. OpenAI is reported to say the tests are deliberately hard and are not estimates of real-world rates. The system card link in that article is broken, so the card was not read for this piece.

7. Frequently asked questions

Is there no token charge at all? Not for the voice session, which is billed by time alone. But whatever the backend model does in reasoning and tool calls is billed at that model's token rates. Tokens do not disappear from the invoice; they move to a separate line.

Does the rate drop to $0.02 automatically when the user stops talking? No. The session must use WebRTC, an idle timeout must be set, and the session must actually enter the paused state. Without a timeout, the session stays at the active rate after the first wake.

Does muting the microphone stop the meter? No. Data Studios says muting does not close the session. To stop charges, end the session. To lower them, send it to standby.

Does standby apply to phone calls over SIP? That is not settled. The model page says only that standby applies to WebRTC. The DEV Community post says SIP and WebSocket pay the active rate throughout, but the primary source does not go that far. Phone-based services are safer budgeting as if standby were unavailable.

Are calls under a minute rounded up? Two secondary sources say billing is per second with no rounding. On that basis a 90-second call costs $0.075. The model page says only that sessions are billed by duration, so this needs confirming on the pricing page.

Is it cheaper than GPT-Realtime? It cannot be said in general. One bills by the minute and the other by the token, and the sources read for this article do not give the number of audio tokens in a minute of conversation. The most that can be said is that services with long silences are structurally better served by GPT-Live-1.1, which has a standby rate.

Should I migrate from GPT-Live-1? The active rate is the same. The improvements OpenAI cites, transcription accuracy and cross-language voice consistency, are not quantified. Because the two models have separate concurrency limits, both can run side by side during a migration. The statement that GPT-Live-1 also gets standby pricing from the same date comes from one source and needs checking.

Is this the same model as ChatGPT voice? Data Studios says GPT-Live-1.1 is now the default voice for ChatGPT Plus and higher tiers. That is one source, and it adds that the variant described for other users is not on the API pricing page.

Can I get responses as JSON? The voice model does not support structured outputs. Values that need a format should come through function call arguments or be handled by the backend model.

What does a dollar buy? Twenty active minutes or fifty standby minutes of voice session time, before backend charges. That is this article's arithmetic from the published per-minute rates.

8. What remains open and unconfirmed

ItemConfirmedNot confirmed
Rates$0.05 active, $0.02 standby per minute (OpenAI model page)The pricing page itself was not opened
Billing basisSession duration (model page)Per-second billing and the 15-second initial charge rest on two secondary sources
Standby conditionWebRTC, inference paused (model page)Whether it extends to WebSocket or SIP; sources diverge
Standby settingsNames and ranges match across two secondary sourcesNot checked against an official sample
Release dateThe cited changelog entry and one report's publication date say November 19, 2026The DEV post says November 20; the model page has no date
Backend costThat it is billed separatelyRecommended models are named only by secondary sources; their rates were not checked
GPT-Realtime comparisonRates and limits from the DEV postThe OpenAI pricing page; audio tokens per minute
Standby for GPT-Live-1One statement by Data StudiosWhether standby first appeared with 1.1
ImprovementsTranscription accuracy, cross-language consistency (model page)Any figures or benchmarks
Safety evaluationSystem card contents as relayed by Superpower DailyThe system card itself
Voices, languages, latency—None published
ConcurrencyThat 1.1 and 1 are counted separatelyPer-tier numbers for 1.1
ChatGPT rolloutOne statement by Data StudiosAn OpenAI announcement

In short: the GPT-Live-1.1 API costs $0.05 per active minute and $0.02 per standby minute, and standby applies only when a developer sets an idle timeout on a WebRTC session and the session actually pauses. The more silence a service has, the more it saves; a call with no gaps saves nothing. The backend model is billed on top, so the per-minute figure is the floor of the bill. With voices, languages, latency and concurrency limits still unpublished, the remaining questions have to be answered with test calls.

For how token rates are built, see the August 15, 2026 explainer "What AI token pricing is — why output costs about 5× input"; for rates that change by time of day, the August 16, 2026 explainer "What peak pricing for AI APIs is — the same prompt, twice the cost"; and for the risks that come with synthetic voices, the October 7, 2026 explainer "What voice cloning is — how 3 seconds of audio copies a voice, and how to stop it".

Sources

  1. OpenAI developer docs — GPT-Live-1.1 model page
  2. Data Studios — OpenAI GPT-Live-1.1 API: $0.05/min active, new $0.02/min standby mode
  3. DEV Community — GPT-Live-1.1 vs GPT-Realtime: Which OpenAI Voice API to Use (2026-11-20)
  4. Superpower Daily — OpenAI brings GPT-Live-1.1 to developers with lower-priced standby sessions (2026-11-19)

Verification

Published
Last modified
Cross-check
Checked against 4 independent sources.
Unverified
  • The rates ($0.05 active, $0.02 standby, the WebRTC and paused-inference condition, separate backend billing) were confirmed on the OpenAI model page. The OpenAI pricing page, the Live API guides and the changelog itself were not opened.
  • The model page says only that sessions are billed by duration. Per-second billing, and the statement that a WebRTC session bills 15 seconds at initialization and credits them against later duration, come from Data Studios and a DEV Community post and were not checked against OpenAI text.
  • Sources disagree on the API release date. The OpenAI changelog entry cited by Data Studios and the publication date of Superpower Daily point to November 19, 2026; the DEV Community post says November 20. The model page carries no date. This article uses November 19 (US time).
  • Whether standby pricing applies to WebSocket or SIP sessions is unsettled. The model page and Data Studios say only that it applies to WebRTC. The DEV Community post states flatly that WebSocket and SIP bill every connected second at the active rate, which goes further than the primary source.
  • Only Data Studios says the standby rate also applies to the earlier GPT-Live-1 from November 19, 2026. Sources also differ on whether standby is new with 1.1.
  • The setting names (session.wake_policy.type, session.idle_timeout_s, session.wake_policy.vad_threshold) and their ranges match across Data Studios and the DEV Community post, but Data Studios describes its snippet as illustrative, not an official sample. Check OpenAI documentation before relying on them.
  • gpt-6-luna and gpt-6-sol are named as backend models by two secondary sources and do not appear on the model page. Their token prices were not checked for this article.
  • The gpt-realtime-2.1 rates and limits, and the absence of standby there, rest on one DEV Community post. That post lists image input as supported in a table and cites $5 per 1M image tokens in its FAQ, but its pricing table has no image line. None of this was checked against the OpenAI pricing page.
  • The GPT-Live-1 concurrency limits (50 on Build, 300 on Launch, 500 on Grow, no Free tier access) are relayed by secondary sources. Per-tier limits for GPT-Live-1.1 are not published.
  • That GPT-Live-1.1 is now the default ChatGPT voice for Plus and higher tiers, and that older ChatGPT voice modes retire on December 11, 2026, is stated by Data Studios alone.
  • The system card findings (1.1 scoring numerically higher than its predecessor on emotional reliance and self-harm tests) were found only in Superpower Daily, whose system card link is broken. The card itself was not read.
  • No source gives the voice catalog, a language list, latency figures, regional availability, session length limits beyond the two-hour SIP cap, or a quantified transcription gain. The original launch date of GPT-Live-1 was not established.
  • The tutoring, kiosk and support-call cost examples are Data Studios calculations that this article re-checked. The monthly call-volume example and the hourly conversions are this article's own arithmetic and exclude backend costs.
Authoring
Reviewed by a person before publication. The full process is described in the Editorial.

Ten stories, once each morning

We send the three-line summaries only; the full pieces stay on the site. One-click unsubscribe, any time.

Related