This model is hosted by one provider. OpenRouter forwards every request to it directly — no routing decisions to make.
The average price customers actually pay for this model, next to the prices providers post. Caching and discounts mean the price actually paid is often well below the listed one.
Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better).
Uptime is the percentage of the past 3 days that at least one provider was responding to requests. Availability is the percentage of time that inference was successfully served. OpenRouter continuously monitors and uses the next-best provider when one returns an error.
Scores on standardized evaluations. Higher percentages are better — and rank percentile shows where this model lands among all models on OpenRouter.
| Source | Benchmark | Score |
|---|---|---|
| Artificial Analysis | Nova Premier GPQA Diamond | 56.9% |
| Artificial Analysis | Nova Premier HLE | 4.2% |
| Artificial Analysis | Nova Premier IFBench | 36.2% |
| Artificial Analysis | Nova Premier τ²-Bench Telecom | 38.3% |
| Artificial Analysis | Nova Premier AA-LCR | 34.3% |
| Artificial Analysis | Nova Premier CritPt | 0.0% |
| Artificial Analysis | Nova Premier Terminal-Bench Hard | 6.8% |
| Artificial Analysis | Nova Premier AA-Omniscience Accuracy | 21.2% |
| Artificial Analysis | Nova Premier AA-Omniscience Non-Hallucination Rate | 28.1% |
| Design Arena | Amazon Nova Premier Models Arena Website Elo | 847 |
Public apps that send the most traffic to this model. Good signal for what real production workloads look like — and a hint at which use cases this model is best suited for.
Token volume and request traffic to this model over time.
Drop-in code to call this model. OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. The only thing that changes between models is the model slug below.
| $2.50 | $12.50 | $0.625 | 0.87s | 33 tps |
Throughput
33tok/s
P50, best across providers
Latency
0.87s
P50, best provider
100.00%
99.89%
When an error occurs in an upstream provider, we can recover by routing to another healthy provider, if your request filters allow it. You can access per-provider uptime data programmatically through the Endpoints API. Learn more about our load balancing and customization options.
Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.
Nova Premier 1.0 costs $2.50/M input tokens and $12.50/M output tokens, with separate rates for Cache Read at $0.625/M tokens.
Nova Premier 1.0 has a 1,000,000 token context window. It supports up to 32,000 completion tokens.
Yes. Nova Premier 1.0 accepts tools for function calling. It does not support response_format, so JSON output is not enforced.
Nova Premier 1.0 accepts text and images as input and returns text.
Nova 2 Lite, Nova Lite 1.0, Nova Micro 1.0 and 1 more are other text models from Amazon.
Nova Premier 1.0 was released on October 31, 2025.
