Pricingby GlyphAmazon 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.
Ways to buy 2
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
 Amazon Nova APIThe lab's own API · cached $0.625 | $2.5 | $12.5 | $2.5 / $12.5List price | $0.625 | List price |
 AWS BedrockDefault region · cached $0.625 | $2.5 | $12.5 | $2.5 / $12.5Same as list | $0.625 | Same as list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $500.00 direct.
Kong AI Gateway$500.00+0%
LiteLLM$500.00+0%
OpenRouter$527.50+5.5%
Cloudflare AI GatewayNot offeredNot offered
Eden AINot offeredNot offered
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
RequestyNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey, TrueFoundry AI Gateway.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
| Titan Embeddings G1 - Text Amazon Nova · 8K | $0.1 | Free | $0.1 / Free | $0.075 | 8K | Lab list price | · | Amazon Titan Embeddings G1 - Text is the first-generation Titan text embedding model. |
| Titan Multimodal Embeddings G1 Amazon Nova · 0K | $0.8 | Free | $0.8 / Free | $0.6 | 0K | Lab list price | · | Amazon Titan Multimodal Embeddings G1 embeds text, images, or text and image together into a shared vector space for multimodal search and recommendation. |
| Titan Text Embeddings V2 Amazon Nova · 8K | $0.02 | Free | $0.02 / Free | $0.015 | 8K | Lab list price | · | Amazon Titan Text Embeddings V2 is a text embedding model for retrieval, search, and clustering. |
| Nova 2 Lite Amazon Nova · 1M | $0.3 | $2.5 | $0.3 / $2.5 | $0.85 | 1M | Lab list price | · | Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. |
OpenAI · 1.05MCheapest: $2 on OpenAI (flex) | $2 | $10 | $2 / $10 | $4 | 1.05M | $2 on OpenAI (flex) | · | GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. |
Anthropic · 1M | $4 | $20 | $4 / $20 | $8 | 1M | Lab list price | · | Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. |
Google · 1MCheapest: $2 on Google Gemini API (flex) | $2 | $10 | $2 / $10 | $4 | 1M | $2 on Google Gemini API (flex) | · | Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. |
Anthropic · 1M | $2 | $10 | $2 / $10 | $4 | 1M | Lab list price | · | Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. |
About Nova Premier 1.0
Takes text, image in and returns text. First listed Nov 1, 2025. Up to 32K output tokens. Blended price $5 per 1M tokens at 3 input to 1 output. Model id nova-premier-v1.
Price history
List price since Nov 1, 2025, from Internet Archive snapshots of the OpenRouter catalog, then daily reads.
Questions
How much does Nova Premier 1.0 cost?
$2.5 per million input tokens and $12.5 per million output tokens, with cached input at $0.625.
What is the context window of Nova Premier 1.0?
1M tokens, with up to 32K tokens of output.
Where is Nova Premier 1.0 cheapest?
Of 2 routes tracked, AWS Bedrock is cheapest at $2.5 input and $12.5 output per million tokens.