Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Amazon / Nova 2

Nova 2 Omni Preview

Preview multimodal model with text and image generation.

Language models (LLMs)Image generation
previewClosed weightsGeneral purposeImage generation
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
2 of 16 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
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
Not collected
Maximum output
Not collected
Input modalities
Text, Image, Video, AudioSource for Input modalities (opens in a new tab)
Output modalities
Text, ImageSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
Not collected
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

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
Not collected

Exact release ID has not been verified.

Access
Preview pricing is published. Confirm preview access and exact API identifier with AWS.
Regions
Pricing includes global and geo/in-region options; account eligibility not collected.

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Standard · GlobalText input1$0.301M text tokens
Standard · GlobalImage input1$0.301M image tokens
Standard · GlobalVideo input1$0.301M video tokens
Standard · GlobalAudio input1$1.001M audio tokens
Standard · GlobalText output1$2.501M text tokens
Standard · GlobalImage output1$40.001M image tokens
Priority · GlobalText input2$0.501M text tokens
Priority · GlobalImage input2$0.501M image tokens
Priority · GlobalVideo input2$0.501M video tokens
Priority · GlobalAudio input2$1.801M audio tokens
Priority · GlobalText output2$4.401M text tokens
Priority · GlobalImage output2$70.001M image tokens
Flex · GlobalText input3$0.201M text tokens
Flex · GlobalImage input3$0.201M image tokens
Flex · GlobalVideo input3$0.201M video tokens
Flex · GlobalAudio input3$0.501M audio tokens
Flex · GlobalText output3$1.301M text tokens
Flex · GlobalImage output3$20.001M image tokens
Batch · GlobalText input4$0.201M text tokens
Batch · GlobalImage input4$0.201M image tokens
Batch · GlobalVideo input4$0.201M video tokens
Batch · GlobalAudio input4$0.501M audio tokens
Batch · GlobalText output4$1.301M text tokens
Batch · GlobalImage output4$20.001M image tokens
Standard · Geo / in-regionText input5$0.301M text tokens
Standard · Geo / in-regionImage input5$0.301M image tokens
Standard · Geo / in-regionVideo input5$0.301M video tokens
Standard · Geo / in-regionAudio input5$1.101M audio tokens
Standard · Geo / in-regionText output5$2.801M text tokens
Standard · Geo / in-regionImage output5$44.001M image tokens
Priority · Geo / in-regionText input6$0.601M text tokens
Priority · Geo / in-regionImage input6$0.601M image tokens
Priority · Geo / in-regionVideo input6$0.601M video tokens
Priority · Geo / in-regionAudio input6$1.901M audio tokens
Priority · Geo / in-regionText output6$4.801M text tokens
Priority · Geo / in-regionImage output6$77.001M image tokens
Flex · Geo / in-regionText input7$0.201M text tokens
Flex · Geo / in-regionImage input7$0.201M image tokens
Flex · Geo / in-regionVideo input7$0.201M video tokens
Flex · Geo / in-regionAudio input7$0.601M audio tokens
Flex · Geo / in-regionText output7$1.401M text tokens
Flex · Geo / in-regionImage output7$22.001M image tokens
Batch · Geo / in-regionText input8$0.201M text tokens
Batch · Geo / in-regionImage input8$0.201M image tokens
Batch · Geo / in-regionVideo input8$0.201M video tokens
Batch · Geo / in-regionAudio input8$0.601M audio tokens
Batch · Geo / in-regionText output8$1.401M text tokens
Batch · Geo / in-regionImage output8$22.001M image tokens
Built-in toolsWeb grounding9$30.001K requests

Rate conditions

  1. Standard Global pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  2. Priority Global pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  3. Flex Global pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  4. Batch Global pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  5. Standard Geo / in-region pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  6. Priority Geo / in-region pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  7. Flex Geo / in-region pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  8. Batch Geo / in-region pricing, US East (N. Virginia) selection. Preview access and API IDs are not verified. Cache-read discounts shown for supported tiers are not included in these uncached rates.
  9. US East (N. Virginia); tool charges are additional to inference. Pricing does not establish tool eligibility for every account.
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

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)

Sources reviewed