Try Bifrost Enterprise free for 14 days.
Request access

amazon.nova-2-5-sonic Cost Calculator - AWS Bedrock

Calculate the cost of using amazon.nova-2-5-sonic from AWS Bedrock for your AI applications

Pricing data last updated:

amazon.nova-2-5-sonic Cost Calculator

Mode: Realtime

Cost Breakdown

Total Cost$0.0000000000

Pricing Details

Input: $0.0000003300 per token
Output: $0.00000275 per token
[ WE'RE OPEN SOURCE ]

Scale with the Fastest LLM Gateway

Built for enterprise-grade reliability, governance, and scale. Deploy in seconds.

About amazon.nova-2-5-sonic

amazon.nova-2-5-sonic is a realtime model from AWS Bedrock, one of 2 realtime models they offer. It is priced at $0.33 per 1M input tokens and $2.75 per 1M output tokens, ranking 2 out of 42 realtime models by cost and cheaper than 95% of models in this category. amazon.nova-2-5-sonic supports audio input, audio output — one of only 7 realtime models with this combination.

Pricing Information

Input Cost$0.33 per 1M tokens
Output Cost$2.75 per 1M tokens

Note: Use the interactive calculator above to estimate costs for your specific usage patterns.

Model Capabilities

✓Audio Input - Accept audio data as input
✓Audio Output - Generate audio responses

How amazon.nova-2-5-sonic Pricing Compares

At $0.33 per 1M input tokens and $2.75 per 1M output tokens, amazon.nova-2-5-sonic ranks 2 out of 42 realtime models by input cost. It is more affordable compared to the median of $0.75 for realtime models, and is cheaper than 95% of models in this category.

amazon.nova-2-5-sonic is one of 2 AWS Bedrock realtime models, one of only 7 realtime models combining audio input, audio output.

ModelProviderInput / 1M tokensOutput / 1M tokensvs amazon.nova-2-5-sonic
gpt-4o-mini-realtime-preview-2024-12-17Azure$0.66$2.64+100%
gpt-realtime-2.1-miniAzure$0.60$2.40+82%
gpt-realtime-miniAzure$0.60$2.40+82%

Alternatives to amazon.nova-2-5-sonic

Similar realtime models from other providers

Azure
gpt-realtime-2.1-mini
$0.60/1M input
+82% vs amazon.nova-2-5-sonic
Azure
gpt-realtime-mini
$0.60/1M input
+82% vs amazon.nova-2-5-sonic
Azure
gpt-realtime-mini-2025-10-06
$0.60/1M input
+82% vs amazon.nova-2-5-sonic
Vertex AI
gemini-live-2.5-flash-native-audio
$0.50/1M input
+52% vs amazon.nova-2-5-sonic

Frequently Asked Questions

Is amazon.nova-2-5-sonic cheaper than gpt-4o-mini-realtime-preview-2024-12-17?

Yes. amazon.nova-2-5-sonic costs $0.33 per 1M input tokens compared to gpt-4o-mini-realtime-preview-2024-12-17's $0.66 per 1M input tokens, making it 100% more affordable. Both are realtime models and share support for function calling, audio input, audio output.

How does amazon.nova-2-5-sonic pricing compare to the average realtime model?

amazon.nova-2-5-sonic input pricing is $0.33 per 1M tokens, which is 56% below the median of $0.75 for realtime models. It ranks 2 out of 42 realtime models by input cost, making it cheaper than 95% of models in this category. For output, it costs $2.75 per 1M tokens compared to the median of $4.50.

What makes amazon.nova-2-5-sonic different from other AWS Bedrock models?

Among AWS Bedrock's 2 realtime models, amazon.nova-2-5-sonic ranks 2 by input cost. Its combination of audio input, audio output is shared by only 6 other realtime models.

What are the best alternatives to amazon.nova-2-5-sonic?

The most comparable realtime models to amazon.nova-2-5-sonic are: gpt-4o-mini-realtime-preview-2024-12-17 from Azure ($0.66/1M input tokens); gpt-realtime-2.1-mini from Azure ($0.60/1M input tokens); gpt-realtime-mini from Azure ($0.60/1M input tokens); gpt-realtime-mini-2025-10-06 from Azure ($0.60/1M input tokens). These alternatives were selected based on similar capabilities, pricing, and provider diversity. You can compare any of these models in detail using the Bifrost Model Library.

How do I calculate amazon.nova-2-5-sonic costs?

amazon.nova-2-5-sonic is priced based on input and output tokens. Use the interactive calculator at the top of this page to estimate costs for your specific workload. Enter your expected input and output tokens volume and the calculator will show the total cost breakdown. For reference, processing 1M input tokens costs $0.33 and generating 1M output tokens costs $2.75.