Amazon · Model
Nova Premier 1.0 pricing, context window and specs
Nova Premier 1.0 costs $2.50 per million input tokens and $12.50 per million output tokens, and reads up to 1,000,000 tokens per request. By blended price it is the most expensive of Amazon’s 2 current models here.
- Input / 1M
- $2.50
- Output / 1M
- $12.50
- Cached / 1M
- $0.625
- Context
- 1,000,000
- Max output
- 32,000
- Released
- 2025-10-31
Estimate your cost with Nova Premier 1.0Compare all Amazon modelsCount tokens for Nova Premier 1.0
Pricing
Nova Premier 1.0 API pricing
| Price per 1M tokens | Input | Output |
|---|---|---|
| Standard | $2.50 | $12.50 |
| Cached input (read) | $0.625 | – |
Output costs 5.0× the input price, so long replies drive the bill more than long prompts. If your requests share a long fixed prefix, such as a system prompt or tool definitions, caching cuts that part to 25% of the normal input price.
Examples
What Nova Premier 1.0 costs in practice
| Workload | Tokens in / out | Requests/day | Per request | Per month |
|---|---|---|---|---|
| Support chatbot50% cached | 1,500 / 400 | 1,000 | $0.00734 | $223.37 |
| RAG app20% cached | 6,000 / 500 | 500 | $0.019 | $288.96 |
| Coding agent80% cached | 40,000 / 2,000 | 200 | $0.065 | $395.42 |
| Document summariser | 8,000 / 600 | 300 | $0.0275 | $250.94 |
Change any number in the cost calculator.
Context
Context window
Nova Premier 1.0 accepts up to 1,000,000 tokens per request, roughly 750,000 English words or 1,500 pages. That budget is shared between your prompt and the reply, and a single reply is capped at 32,000 tokens.
Filling the whole window with one prompt costs about $2.50 at list price, so for repeated long-document work, retrieval (sending only the relevant parts) or prompt caching is usually much cheaper.
Features
Capabilities
- Image input
- Yes
- Tool / function calling
- Yes
- Reasoning mode
- No
- Prompt caching
- Yes
- Structured output
- Yes
- Open weights
- No
- Accepts
- text, image
- Knowledge cutoff
- Not published
As declared by the provider’s API. It shows a feature exists, not how well it works.
API
Nova Premier 1.0 model ID
- OpenRouter
amazon/nova-premier-v1
Use the OpenRouter ID when calling it through OpenRouter; Amazon’s own API may name it differently. See the model ID reference for the providers we document.
Amazon
Where Nova Premier 1.0 sits in Amazon’s line-up
Ranked by blended price (three parts input to one part output, $5 per 1M for Nova Premier 1.0), it is the most expensive of Amazon’s 2 current models here. One step down, Nova 2 Lite costs $0.85 blended (83% less). Unlike Nova Premier 1.0, it accepts files and video, caps a reply at 65,535 tokens (32,000 here) and has a reasoning mode. See every Amazon model and price
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Nova 2 Lite | $0.30 | $2.50 | 1,000,000 | 2025-12-02 |
| Nova Premier 1.0 (this page) | $2.50 | $12.50 | 1,000,000 | 2025-10-31 |
Amazon’s current models with a page here, cheapest first. Older and superseded models are listed on the provider page and in the comparison table.
Save
Cheaper alternatives
- Qwen3.7 PlusQwen89% cheaper
- GLM 5.3 FlashXZ.ai88% cheaper
- Command A+Cohere88% cheaper
- Seed-2.0-LiteByteDance Seed86% cheaper
- Gemini 3.5 Flash LiteGoogle83% cheaper
Current models from major providers, one per provider, that keep image input, tool calling, a usable context window and output limit. Compared by blended price.
Compare
Similarly priced models
- GPT-5.6 TerraOpenAI$2 / $12
- Gemini 3.1 Pro PreviewGoogle$2 / $12
- GLM 5.3 PrimeZ.ai$2.80 / $8.80
- Qwen3.8 Max PrimeQwen$4 / $12
- Claude Sonnet 5.5Anthropic$2 / $10
Current models from other major providers, closest blended price.
FAQ
Nova Premier 1.0 questions
How much does Nova Premier 1.0 cost?
Nova Premier 1.0 costs $2.50 per million input tokens and $12.50 per million output tokens, with cached input at $0.625. A typical chatbot reply (1,500 tokens in, 400 out) costs about $0.00875. Use the LLM cost calculator for your own workload.
What is Nova Premier 1.0’s context window?
1,000,000 tokens, about 750,000 English words or 1,500 printed pages, shared between your prompt and the reply. A single reply can be up to 32,000 tokens.
Does Nova Premier 1.0 support prompt caching and batch requests?
Yes, cached input is billed at $0.625 per million tokens (25% of the normal input price). No batch price is published for it.
What are cheaper alternatives to Nova Premier 1.0?
With the same essentials (image input and tool calling), the cheapest options are Qwen3.7 Plus (89% cheaper), GLM 5.3 FlashX (88% cheaper), Command A+ (88% cheaper). Cheaper doesn’t mean equivalent, so test them on your own prompts.
What is the API model ID for Nova Premier 1.0?
On OpenRouter it is amazon/nova-premier-v1. Amazon’s own API may use a different name, so check its model list before you deploy. Pass the ID as the model value in each request.
Is Nova Premier 1.0 open source?
No, Nova Premier 1.0 is only available through Amazon’s API and partners; its weights aren’t published.