This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Amazon has launched a newer release, Nova 2.0 Pro Preview. We suggest considering it instead.
Nova Pro API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Nova Pro for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 1 provider
Lowest Cost per Task
Cost per Intelligence Index task
Total 1 provider
Nova Pro is available through Amazon.
Pricing
Cost per Intelligence Index Task: Nova Pro
Pricing: Cache Hit, Input, and Output: Nova Pro
Output Speed vs. Cost per Task: Nova Pro
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Nova Pro
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Nova Pro
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Nova Pro
Caching
Cache Hit Rate: Nova Pro
Cost per Task vs. Cache Hit Rate: Nova Pro
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Nova Pro providers
Nova Pro is available through 1 API provider: Amazon. Each provider offers different performance characteristics and pricing.
Nova Pro is currently available through 1 API provider that we benchmark and track.
The provider with the lowest time to first answer token for Nova Pro is Amazon (2.63s). Lower latency means faster initial response time.
The most affordable provider for Nova Pro by blended price is Amazon ($0.62 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for Nova Pro is Amazon ($0.80 per 1M input tokens).
The provider with the lowest output token pricing for Nova Pro is Amazon ($3.20 per 1M output tokens).
The only provider of Nova Pro supports function calling (tool use).
When choosing a provider for Nova Pro, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Nova Pro's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview