Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Amazon / Nova 1

Nova Pro

Multimodal language model for text, image and video understanding.

Language models (LLMs)
availableClosed weightsGeneral purposeDocument analysis
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
12 of 17 specification fields collected
Context window300K300,000 tokens
Maximum output10K10,000 tokens
Input / 1M tokens$0.80Amazon Bedrock
Output / 1M tokens$3.20USD · observed 12 Oct 2026

Specifications

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

Context / input limit
300,000 tokensSource for Context / input limit (opens in a new tab)

Card publishes 300K tokens. More precise specialist limits are used when documented.

Maximum output
10,000 tokensSource for Maximum output (opens in a new tab)
Input modalities
Image, Text, VideoSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
SupportedSource for Batch processing (opens in a new tab)
Fine-tuning
SupportedSource for Fine-tuning (opens in a new tab)
Knowledge cutoff
Oct 2024Source for Knowledge cutoff (opens in a new tab)
Release date
2024-12-04Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Not collected
Languages
200+; 15 optimized languagesSource for Languages (opens in a new tab)
API aliases
us.amazon.nova-pro-v1:0, eu.amazon.nova-pro-v1:0, apac.amazon.nova-pro-v1:0Source for API aliases (opens in a new tab)

Inference profiles route requests to this release; they are not separate models.

Context caching
SupportedSource for Context caching (opens in a new tab)

Documented on at least one recorded endpoint. See Caching for host, lifecycle and billing restrictions.

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-pro-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), eu-west-2 (London), ap-southeast-2 (Sydney), ap-southeast-3 (Jakarta), me-central-1 (UAE). Geo profile source regions: us-east-1 (N. Virginia), us-east-2 (Ohio), us-west-1 (N. California), us-west-2 (Oregon), eu-central-1 (Frankfurt), eu-north-1 (Stockholm), eu-south-1 (Milan), eu-south-2 (Spain), eu-west-1 (Ireland), eu-west-3 (Paris), ap-east-2 (Taipei), ap-northeast-1 (Tokyo), ap-northeast-2 (Seoul), ap-south-1 (Mumbai), ap-southeast-1 (Singapore), ap-southeast-2 (Sydney), ap-southeast-3 (Jakarta), ap-southeast-4 (Melbourne), ap-southeast-5 (Malaysia), ap-southeast-7 (Thailand), il-central-1 (Tel Aviv), me-central-1 (UAE)
INPUT / 1M TOKENS$0.80
OUTPUT / 1M TOKENS$3.20

Standard; Geo cross-region / in-region; US East (N. Virginia) pricing selection. Published 2026-10-10T18:22:42Z. Regional eligibility and quotas are separate from the published rate. Cached input price: not collected.

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Priority · Geo cross-region / in-regionInput1$1.401M tokens
Priority · Geo cross-region / in-regionOutput1$5.601M tokens
Flex · Geo cross-region / in-regionInput2$0.401M tokens
Flex · Geo cross-region / in-regionOutput2$1.601M tokens
Batch · Geo cross-region / in-regionInput3$0.401M tokens
Batch · Geo cross-region / in-regionOutput3$1.601M tokens
Text tokensCache read4$0.201M tokens

Rate conditions

  1. Priority; Geo cross-region / in-region; US East (N. Virginia) pricing selection. Published 2026-10-10T18:22:42Z. Regional eligibility and quotas are separate from the published rate.
  2. Flex; Geo cross-region / in-region; US East (N. Virginia) pricing selection. Published 2026-10-10T18:22:42Z. Regional eligibility and quotas are separate from the published rate.
  3. Batch; Geo cross-region / in-region; US East (N. Virginia) pricing selection. Published 2026-10-10T18:22:42Z. Regional eligibility and quotas are separate from the published rate.
  4. Dedicated on-demand caching table; US East (N. Virginia) price selection. Nova 2 Lite base input matches the global-profile rate. Do not apply this rate to other routing or service tiers.
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)

Amazon Bedrock

Provider source (opens in a new tab)
API model ID
us.amazon.nova-pro-v1:0
Access
Inference profile routes to the same model. Cross-region routing does not guarantee execution in the source region.
Regions
Geo cross-region profile us. Confirm source and destination regions in the card.

Endpoint pricing has not been collected. Check the provider for applicable rates.

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)

Amazon Bedrock

Provider source (opens in a new tab)
API model ID
eu.amazon.nova-pro-v1:0
Access
Inference profile routes to the same model. Cross-region routing does not guarantee execution in the source region.
Regions
Geo cross-region profile eu. Confirm source and destination regions in the card.

Endpoint pricing has not been collected. Check the provider for applicable rates.

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)

Amazon Bedrock

Provider source (opens in a new tab)
API model ID
apac.amazon.nova-pro-v1:0
Access
Inference profile routes to the same model. Cross-region routing does not guarantee execution in the source region.
Regions
Geo cross-region profile apac. Confirm source and destination regions in the card.

Endpoint pricing has not been collected. Check the provider for applicable rates.

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-pro-v1:0
Documented
Support evidence (opens in a new tab)
How it works
Implicit text-prefix reuse + explicit checkpointsSource for How it works (opens in a new tab)
Minimum reusable input
1K tokens before a checkpoint; maximum cached prefix 20K tokens.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
5 minutes; refreshed by a successful cache hit.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Up to four checkpoints in system and messages. Use cachePoint with type default. Do not request the unsupported 1h TTL.Source for How to enable it (opens in a new tab)
Usage fields
Converse: cacheReadInputTokens and cacheWriteInputTokens.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the endpoint-specific discounted rate. Verify write pricing for the selected service tier.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Primarily text prompts; on-demand inference only. No batch inference caching. Cross-region routing can reduce reuse and cause additional writes.Source for Limits & data boundaries (opens in a new tab)
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens$0.20 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Dedicated on-demand caching table; US East (N. Virginia) price selection. Nova 2 Lite base input matches the global-profile rate. Do not apply this rate to other routing or service tiers.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 12 Oct 2026

Amazon Bedrock

us.amazon.nova-pro-v1:0
Documented
Support evidence (opens in a new tab)
How it works
Implicit text-prefix reuse + explicit checkpointsSource for How it works (opens in a new tab)
Minimum reusable input
1K tokens before a checkpoint; maximum cached prefix 20K tokens.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
5 minutes; refreshed by a successful cache hit.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Up to four checkpoints in system and messages. Use cachePoint with type default. Do not request the unsupported 1h TTL.Source for How to enable it (opens in a new tab)
Usage fields
Converse: cacheReadInputTokens and cacheWriteInputTokens.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the endpoint-specific discounted rate. Verify write pricing for the selected service tier.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Primarily text prompts; on-demand inference only. No batch inference caching. Cross-region routing can reduce reuse and cause additional writes.Source for Limits & data boundaries (opens in a new tab)

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

Caching reviewed 12 Oct 2026

Amazon Bedrock

eu.amazon.nova-pro-v1:0
Documented
Support evidence (opens in a new tab)
How it works
Implicit text-prefix reuse + explicit checkpointsSource for How it works (opens in a new tab)
Minimum reusable input
1K tokens before a checkpoint; maximum cached prefix 20K tokens.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
5 minutes; refreshed by a successful cache hit.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Up to four checkpoints in system and messages. Use cachePoint with type default. Do not request the unsupported 1h TTL.Source for How to enable it (opens in a new tab)
Usage fields
Converse: cacheReadInputTokens and cacheWriteInputTokens.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the endpoint-specific discounted rate. Verify write pricing for the selected service tier.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Primarily text prompts; on-demand inference only. No batch inference caching. Cross-region routing can reduce reuse and cause additional writes.Source for Limits & data boundaries (opens in a new tab)

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

Caching reviewed 12 Oct 2026

Amazon Bedrock

apac.amazon.nova-pro-v1:0
Documented
Support evidence (opens in a new tab)
How it works
Implicit text-prefix reuse + explicit checkpointsSource for How it works (opens in a new tab)
Minimum reusable input
1K tokens before a checkpoint; maximum cached prefix 20K tokens.Source for Minimum reusable input (opens in a new tab)
Lifetime & refresh
5 minutes; refreshed by a successful cache hit.Source for Lifetime & refresh (opens in a new tab)
How to enable it
Up to four checkpoints in system and messages. Use cachePoint with type default. Do not request the unsupported 1h TTL.Source for How to enable it (opens in a new tab)
Usage fields
Converse: cacheReadInputTokens and cacheWriteInputTokens.Source for Usage fields (opens in a new tab)
Billing rules
Cache reads use the endpoint-specific discounted rate. Verify write pricing for the selected service tier.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Primarily text prompts; on-demand inference only. No batch inference caching. Cross-region routing can reduce reuse and cause additional writes.Source for Limits & data boundaries (opens in a new tab)

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

Caching reviewed 12 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

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)4 Dec 2024Source (opens in a new tab)

Sources reviewed