Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Zhipu AI / Z.ai / GLM realtime

GLM-Realtime-Flash

Realtime voice and video conversation with streaming audio, interruption handling and function calling.

Speech & voice
availableClosed weightsVoice conversationSpeech-to-speech
Official documentation (opens in a new tab)Reviewed 13 Oct 2026
10 of 20 specification fields collected
Output formatsPCM, mono, 16-bitSee specification notes below
LanguagesNot collectedAwaiting source review
Input billingSee ratesBigModel China
Output billingSee ratesPublished units and conditions below

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Audio calls: 8K; video calls: 32KSource for Context / input limit (opens in a new tab)

Call-mode limits, not different model sizes. The guide estimates about 20 audio conversation turns.

Maximum output
1,024 tokensSource for Maximum output (opens in a new tab)

max_response_output_tokens counts the response text tokens. This is not a maximum audio duration.

Input modalities
Text, Audio, VideoSource for Input modalities (opens in a new tab)
Output modalities
AudioSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
Not collected
Output formats
PCM, mono, 16-bitSource for Output formats (opens in a new tab)
Audio sample rates
24000 Hz outputSource for Audio sample rates (opens in a new tab)
inputAudioFormats
WAV, PCM (specify sample rate, for example pcm16 or pcm24)Source for inputAudioFormats (opens in a new tab)
Voice controls
Client VAD, Server VAD, Interruptions, Six system voicesSource for Voice controls (opens in a new tab)

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

BigModel China

Provider source (opens in a new tab)
API model ID
glm-realtime-flash
Access
Provider account and authorized service access required. Public documentation reviewed; no paid inference performed.
Regions
Native open.bigmodel.cn service. Account eligibility and deployment region require provider confirmation; international Z.ai terms are not assumed.
API endpoint URL
wss://open.bigmodel.cn/api/paas/v4/realtimeSource for API endpoint URL (opens in a new tab)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 13 Oct 2026
CategoryUsageRateUnit
Realtime audioAudio call1CN¥0.18minute
Realtime videoVideo call2CN¥1.20minute

Rate conditions

  1. Audio-call mode. No unsupported input/output token split or billing-rounding assumption. Published Chinese yuan rates, without currency conversion. Account quotas, contracts and separate service charges may apply.
  2. Video-call mode. This is not the audio-only call rate. Published Chinese yuan rates, without currency conversion. Account quotas, contracts and separate service charges may apply.
Pricing source (opens in a new tab)

Data & enterprise terms

BigModel service terms sections 4.4 and 4.6 address customer data ownership and minimum necessary storage with anonymization and encryption. This is not a zero-retention or no-training guarantee.

Read the service policy (opens in a new tab)

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

BigModel China

glm-realtime-flash
Not verified
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Voice choices

6 voices

Choose a voice within GLM-Realtime-Flash. These are API voice identifiers, not additional model releases. Source links document each voice.

Published voice catalog
Voice / API IDLanguage & accentDelivery
tongtongtongtongNot specified per voiceDefault system voiceVoice source (opens in a new tab)
female-tianmeifemale-tianmeiNot specified per voiceSystem voiceVoice source (opens in a new tab)
male-qn-daxueshengmale-qn-daxueshengNot specified per voiceSystem voiceVoice source (opens in a new tab)
male-qn-jingyingmale-qn-jingyingNot specified per voiceSystem voiceVoice source (opens in a new tab)
lovely_girllovely_girlNot specified per voiceSystem voiceVoice source (opens in a new tab)
female-shaonvfemale-shaonvNot specified per voiceSystem voiceVoice source (opens in a new tab)

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inferred from the exact named native model service in the official BigModel catalog and API or managed-service documentation, cross-checked against the developer’s public-weight inventory. No weights for this exact release were found in that inventory. A paid endpoint alone is not the basis: downloadable GLM releases and uncertain aliases are excluded pending exact mapping.

Classification evidence (opens in a new tab)

Sources reviewed