One video/request, up to 120 frames. At default 1 FPS this is 120 seconds before the shared token cap. MOV/MP4 with AV1, H264, H265 or VP9. Audio extraction is off by default.Source for Source video limits (opens in a new tab)
All modalities share 8,192 tokens and overage is silently truncated. Audio: 25 tokens/sec; video: 66/frame; image: 258/image; PDF: 258/page plus OCR text. With 1 FPS video and extracted audio, timestamps add 10 tokens/sec, yielding about 81 seconds at the full budget.Source for Billing and deployment scope (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.
Cloud Storage JSONL only, no BigQuery. Up to 1,000,000 rows and 1 GB per job. Dynamic scheduling, up to 72 hours queued, target completion under 24 hours.Source for Batch limits (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Embedding 2 family rate (preview label in source)
Text input1
$0.20
1M text tokens
Embedding 2 family rate (preview label in source)
Image input1
$0.45
1M image tokens
Embedding 2 family rate (preview label in source)
Video input1
$12.00
1M video tokens
Embedding 2 family rate (preview label in source)
Audio input1
$6.50
1M audio tokens
Embedding inference
Embedding output2
$0.00
output response
Rate conditions
Pricing table labels this Gemini Embedding 2 family row Preview, while the current model guide uses the stable selector. Version-specific applicability should be confirmed before budgeting; output is free.
No output charge is listed; input charges and model-version conditions apply.
Cloud Storage JSONL only, no BigQuery. Up to 1,000,000 rows and 1 GB per job. Dynamic scheduling, up to 72 hours queued, target completion under 24 hours.Source for Batch limits (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Embedding 2 family rate (preview label in source)
Text input1
$0.10
1M text tokens
Embedding 2 family rate (preview label in source)
Image input1
$0.225
1M image tokens
Embedding 2 family rate (preview label in source)
Video input1
$6.00
1M video tokens
Embedding 2 family rate (preview label in source)
Audio input1
$3.25
1M audio tokens
Embedding inference
Embedding output2
$0.00
output response
Rate conditions
Pricing table labels this Gemini Embedding 2 family row Preview, while the current model guide uses the stable selector. Version-specific applicability should be confirmed before budgeting; output is free.
No output charge is listed; input charges and model-version conditions apply.
Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.
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.
Google Gemini API
gemini-embedding-2
Not verified
Provider-side caching has not been verified for this endpoint. Missing documentation is not evidence that caching is unsupported.
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.
Google Enterprise Agent Platform (online)
gemini-embedding-2
Not verified
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
How it works
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Minimum reusable input
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Lifetime & refresh
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
How to enable it
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Usage fields
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Billing rules
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Limits & data boundaries
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
Google Enterprise Agent Platform (batch)
gemini-embedding-2
Not verified
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
How it works
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Minimum reusable input
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Lifetime & refresh
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
How to enable it
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Usage fields
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Billing rules
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
Limits & data boundaries
Not collected
Caching for this embedding endpoint is not established by the reviewed model docs. Generative Gemini prompt-cache support is not assumed.
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
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
Google-documented proprietary hosted release in the Gemini API model catalog. No public weights identified for this release in the reviewed documentation; public-weight Gemma models are excluded.
