Specialized conversation summarization API model family for recaps, detailed summaries and action items. It returns rendered text, with character-based billing.
English (en-US), Chinese Simplified (zh-CN), Japanese (ja-JP), Spanish (es-ES), French (fr-FR), German (de-DE), Portuguese (pt-BR), Italian (it-IT), Arabic Saudi Arabia (ar-SA), Arabic UAE (ar-AE)Source for Languages (opens in a new tab)
Output locales; input language is not supplied explicitly. English is the default output.
The response example reports zoom-summarizer-v1; requests select the service route and language, not a pinned checkpoint. This is not an independently selectable model ID.
Access
POST /v2/aiservices/summarizer/summarize with inline text and config. API key or short-lived JWT through Zoom Platform Studio.
Regions
Cloud service; model-specific execution regions and residency options require account confirmation
Input byte size, not a 96K-token context window. Batch has the same per-file size limit.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Text processing
Conversation summarization1
$0.40
1M input characters
Text processing
Conversation summarization · India price2
₹37.00
1M input characters
Rate conditions
Published service rate, not a per-token rate. Source text characters are the billing unit; no output-token price or token-based question estimate is inferred. Product pricing applies to Fast and Batch; exact Unicode counting and rounding require the account billing contract.
Published INR storefront rate, excluding GST. Alternative regional price; not an additional charge or inferred FX conversion.
Zoom’s terms say communications-like Customer Content is not used to train Zoom or third-party AI models. This does not establish zero retention: operational data, configured storage and service-generated data have separate handling. No API-specific numeric retention window or execution region was verified.
The response example reports zoom-summarizer-v1; requests select the service route and language, not a pinned checkpoint. This is not an independently selectable model ID.
Access
POST /v2/aiservices/summarizer/jobs with S3 SINGLE, PREFIX or MANIFEST inputs, output destination and optional signed completion webhook.
Regions
Cloud service; model-specific execution regions and residency options require account confirmation
Subtitle timestamps and formatting are removed before inference.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 13 Oct 2026
Category
Usage
Rate
Unit
Text processing
Conversation summarization1
$0.40
1M input characters
Text processing
Conversation summarization · India price2
₹37.00
1M input characters
Rate conditions
Published service rate, not a per-token rate. Source text characters are the billing unit; no output-token price or token-based question estimate is inferred. Product pricing applies to Fast and Batch; exact Unicode counting and rounding require the account billing contract.
Published INR storefront rate, excluding GST. Alternative regional price; not an additional charge or inferred FX conversion.
Zoom’s terms say communications-like Customer Content is not used to train Zoom or third-party AI models. This does not establish zero retention: operational data, configured storage and service-generated data have separate handling. No API-specific numeric retention window or execution region was verified.
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.
Zoom AI Services · fast
Not verified
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Zoom AI Services · batch
Not verified
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
How it works
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Minimum reusable input
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Lifetime & refresh
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
How to enable it
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Usage fields
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Billing rules
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
Limits & data boundaries
Not collected
No model-specific discounted prompt-cache contract was verified. Audio buffering, S3 job storage and orchestration memory are not treated as prompt caching.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
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
Zoom identifies these as its native models or specialized model families supplied through licensed services or internal research. Its terms reserve software rights and prohibit reverse engineering. Public-weight partner models and orchestration products are excluded; no downloadable weight release is established for these named records.
