Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Amazon / Nova Embeddings

Nova Multimodal Embeddings

Shared vector representations for text, images, documents, audio and video.

Embeddings
availableClosed weightsEmbeddings
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
12 of 20 specification fields collected
Input token limit8.2K8,172 tokens
Vector dimensions3072 (default), 1024, 384, 256See specification notes below
Input billingSee ratesAmazon Bedrock
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
8,172 tokensSource for Context / input limit (opens in a new tab)

Per-input text limit in the service card; guide rounds to 8K. Large media can be segmented asynchronously.

Maximum output
Not collected
Input modalities
Audio, Image, Text, VideoSource for Input modalities (opens in a new tab)
Output modalities
EmbeddingsSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not supportedSource for Streaming (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
Not collected
Knowledge cutoff
2025-10-28Source for Knowledge cutoff (opens in a new tab)
Release date
2025-10-27Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Transformer encoder with optional embedding dimension reductionSource for Architecture (opens in a new tab)
Languages
Not collected
Embedding dimensions
3072 (default), 1024, 384, 256Source for Embedding dimensions (opens in a new tab)
Video duration
30 seconds per segmentSource for Video duration (opens in a new tab)
Audio duration limits
30 seconds per segmentSource for Audio duration limits (opens in a new tab)
Supported API routes
InvokeModel (synchronous), StartAsyncInvoke (segmented asynchronous)Source for Supported API routes (opens in a new tab)
Context caching
Not collected

See endpoint caching records. No verified support claim for this model.

Access & pricing

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

Amazon Bedrock

Provider source (opens in a new tab)
API model ID
amazon.nova-2-multimodal-embeddings-v1:0
Access
AWS account and model access required. Verify account quotas and regional eligibility.
Regions
In-region: us-east-1 (N. Virginia), us-gov-west-1 (GovCloud)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
On-demand embeddingsText input1$0.1351M text tokens
On-demand embeddingsStandard image1$0.00006image
On-demand embeddingsDocument image1$0.0006document image
On-demand embeddingsVideo input1$0.0007video second
On-demand embeddingsAudio input1$0.00014audio second
Batch embeddingsText input1$0.06751M text tokens
Batch embeddingsStandard image1$0.00003image
Batch embeddingsDocument image1$0.00048document image
Batch embeddingsVideo input1$0.00056video second
Batch embeddingsAudio input1$0.000112audio second

Rate conditions

  1. US East (N. Virginia). Each modality has its own billing unit; batch discounts differ by modality.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

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.

Amazon Bedrock

amazon.nova-2-multimodal-embeddings-v1:0
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.

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

Amazon-developed managed release. The reviewed release documentation exposes service access, not downloadable model weights.

Classification evidence (opens in a new tab)

Lifecycle dates

Bedrock launch (model card)27 Oct 2025Source (opens in a new tab)

Sources reviewed