Nova 2 Pro (Preview) API pricing
Updated
The cheapest standard price for Nova 2 Pro (Preview) is Amazon (Bedrock) at USD 1.375 per 1M input tokens and USD 11 per 1M output tokens. That is Amazon (Bedrock)'s own API. Every price is read from the provider's own pricing page, checked 2026-11-14.
What does Amazon (Bedrock) charge for Nova 2 Pro (Preview)?
- Input
- USD 1.375
- Cached input
- not published
- Output
- USD 11
- Blended 3:1
- USD 3.781
USD per 1M tokens on Amazon Nova (Bedrock), model Amazon Nova 2 Pro (Preview), standard tier. Source, checked 2026-11-14.
Other Amazon (Bedrock) tiers: batch USD 0.6875 / USD 5.50 · priority USD 2.40625 / USD 19.25 · flex / spot USD 0.6875 / USD 5.50.
Is a host cheaper than Amazon (Bedrock)? Only Amazon (Bedrock) publishes a standard price for Nova 2 Pro (Preview): USD 1.375 input and USD 11 output per 1M tokens. No third-party host lists it on its own pricing page yet.
Nova 2 Pro (Preview) price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Amazon (Bedrock) cheapest makerAmazon Nova 2 Pro (Preview)Notes and source quoteBedrock "Geo Cross-region inference and in-region" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M. “Standard Tier ... Amazon Nova 2 Pro (Preview) $1.375 ... $11.00” | USD 1.375 | not published | USD 11 | USD 3.781 | not stated | not stated | Amazon (Bedrock) page checked 2026-11-14 re-checked 2026-11-16 |
| — | Amazon (Bedrock) maker batchAmazon Nova 2 Pro (Preview)Notes and source quoteBedrock "Geo Cross-region inference and in-region" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M. “Batch ... Amazon Nova 2 Pro (Preview) $0.6875 ... $5.50” | USD 0.6875 | not published | USD 5.50 | USD 1.891 | not stated | not stated | Amazon (Bedrock) page checked 2026-11-14 re-checked 2026-11-16 |
| — | Amazon (Bedrock) maker flex / spotAmazon Nova 2 Pro (Preview)Notes and source quoteBedrock "Geo Cross-region inference and in-region" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M. “Flex Tier ... Amazon Nova 2 Pro (Preview) $0.6875 ... $5.50” | USD 0.6875 | not published | USD 5.50 | USD 1.891 | not stated | not stated | Amazon (Bedrock) page checked 2026-11-14 re-checked 2026-11-16 |
| — | Amazon (Bedrock) maker priorityAmazon Nova 2 Pro (Preview)Notes and source quoteBedrock "Geo Cross-region inference and in-region" table; the page shows Region: US East (Ohio) for the Nova tables (no region picker). Bedrock says cache read input tokens are 75% less than the on-demand input price, but publishes no per-model cached figure. Preview. Text input and text output prices. Global cross-region inference is cheaper: 1.25 input, 10.00 output per 1M. “Priority Tier ... Amazon Nova 2 Pro (Preview) $2.40625 ... $19.25” | USD 2.40625 | not published | USD 19.25 | USD 6.617 | not stated | not stated | Amazon (Bedrock) page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Other tiers (batch, flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Nova 2 Pro (Preview) cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| Amazon (Bedrock) (maker) | USD 321.75 | USD 495.00 | USD 3,465 |
Estimate your own bill
- LLM API cost calculator with Nova 2 Pro (Preview) preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
Priced closest from other makers: Kimi K3.1 Pro (Moonshot AI, USD 3.80) · Kimi K3 (Moonshot AI, USD 3.763) · Claude Sonnet 5 (Anthropic, USD 4).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Nova 2 Pro (Preview) API cost per token?
From USD 1.375 per 1M input tokens (USD 0.000001375 per token) and USD 11 per 1M output tokens (USD 0.000011 per token) at the cheapest standard price. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Nova 2 Pro (Preview)?
Amazon (Bedrock) is the only provider with a paid standard price, USD 1.375 input and USD 11 output per 1M tokens, so there is nothing to rank yet.
Is Nova 2 Pro (Preview) cheaper from a host than from Amazon (Bedrock)?
Only Amazon (Bedrock) publishes a standard price for Nova 2 Pro (Preview): USD 1.375 input and USD 11 output per 1M tokens. No third-party host lists it on its own pricing page yet.
Does Nova 2 Pro (Preview) have cached input pricing?
The only standard price has no cached-input price, so budget repeated prompts at the full input price.
How much does a coding agent cost per month on Nova 2 Pro (Preview)?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 3,465 a month at Amazon (Bedrock). Most of the input is cached, so the cache price matters as much as the input price. Try your own numbers.
Is there a batch, flex or priority price for Nova 2 Pro (Preview)?
Yes: batch from Amazon (Bedrock) at USD 0.6875 / USD 5.50; flex / spot from Amazon (Bedrock) at USD 0.6875 / USD 5.50; priority from Amazon (Bedrock) at USD 2.40625 / USD 19.25 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Nova 2 Pro (Preview) free to use through an API?
No provider in our data lists a free price for Nova 2 Pro (Preview) as of 2026-11-14. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.