Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Amazon / Nova Sonic

Nova 2 Sonic

Conversational speech model with spoken and text input and output.

Speech & voice
availableClosed weightsVoice conversationSpeech-to-speech
Official documentation (opens in a new tab)Reviewed 12 Oct 2026
9 of 16 specification fields collected
Context window1M1,000,000 tokens
Maximum output64K tokens (published)See 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
1,000,000 tokensSource for Context / input limit (opens in a new tab)

Card publishes 1M tokens. More precise specialist limits are used when documented.

Maximum output
64K tokens (published)Source for Maximum output (opens in a new tab)
Input modalities
Speech, TextSource for Input modalities (opens in a new tab)
Output modalities
Speech, TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
SupportedSource for Tool calling (opens in a new tab)
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not disclosedSource for Knowledge cutoff (opens in a new tab)

AWS explicitly does not define a training cutoff for this service.

Release date
2025-12-01Source for Release date (opens in a new tab)
Parameters
Not collected
Architecture
Speech encoder and renderer with a core transformer language modelSource for Architecture (opens in a new tab)
Languages
English, Spanish, German, French, Italian, Portuguese, HindiSource for Languages (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-sonic-v1:0
Access
AWS account and model access required. Verify account quotas and regional eligibility.
Regions
In-region: us-east-1 (N. Virginia), us-west-2 (Oregon), eu-north-1 (Stockholm), ap-northeast-1 (Tokyo)

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
SpeechInput1$3.001M speech tokens
SpeechOutput1$12.001M speech tokens
TextInput1$0.331M text tokens
TextOutput1$2.751M text tokens

Rate conditions

  1. Standard on-demand; US East (N. Virginia). Text billing applies to text history, transcripts and tool exchanges; speech tokens use separate rates.
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-sonic-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)1 Dec 2025Source (opens in a new tab)

Sources reviewed