// head_to_head
Nova Pro 1.0 vs Step 5 Preview
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
Nova Pro 1.0 and Step 5 Preview are priced within ~10% of each other.
Nova Pro 1.0 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
amazon
Nova Pro 1.0
- Blended / 1M
- $1.40
- Context
- 300K
- Released
- Dec 5, 2024
- Overall score
- Not evaluated
stepfun
Step 5 Preview
- Blended / 1M
- $1.43
- Context
- 1.0M
- Released
- Oct 8, 2026
- Overall score
- 58.6
Specs and pricing
| Metric | Nova Pro 1.0 | Step 5 Preview |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | — | 58.6 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | — | $0.0124 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.40 | $1.43 |
| Input price / 1M | $0.800win | $1.00 |
| Output price / 1M | $3.20 | $2.70win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | — | $0.100 |
| Context window | 300K | 1.0Mwin |
| Max output tokens | 5K | 64Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Nova Pro 1.0 on top, Step 5 Preview below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | Nova Pro 1.0 | Step 5 Preview |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $448.00/mo | $391.20/mo |
| RAG assistant 8K in / 600 out × 100K requests | $832.00/mo | $602.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $896.00/mo | $512.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,040/mo | $1,158/mo |
| Bulk classification 500 in / 20 out × 5M requests | $2,320/mo | $2,320/mo |
Which should you pick?
You need to fit large documents in one call
Step 5 Preview
Wider context window — 1.0M against 300K.
Nova Pro 1.0 vs Step 5 Preview FAQ
Which is better, Nova Pro 1.0 or Step 5 Preview?
Nova Pro 1.0 and Step 5 Preview are priced within ~10% of each other. Nova Pro 1.0 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is Nova Pro 1.0 cheaper than Step 5 Preview?
They cost about the same. Both land near $1.40 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does Nova Pro 1.0 or Step 5 Preview have a bigger context window?
Step 5 Preview has the larger context window: 300K for Nova Pro 1.0 against 1.0M for Step 5 Preview. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do Nova Pro 1.0 and Step 5 Preview support prompt caching?
Step 5 Preview publishes a cached-input rate of $0.100 per million tokens against a full input rate of $1.00. The catalogue lists no separate cached rate for Nova Pro 1.0, which means the provider does not price it separately here — not that caching is unavailable.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-10-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.