Skip to content
ModelCap

Nova Pro 1.0

Current board #185Arena #277API only7d #173 → #185

Amazon·amazon/nova-pro-v1

Nova Pro 1.0 is ModelCap current-board rank #185 with Index 21.0 (Measured), from the ModelCap Index as of 22 Sept 2026, 02:49 UTC.

Nova Pro 1.0 listed OpenRouter input price is $0.80 per 1M tokens and listed output price is $3.20 per 1M tokens, from OpenRouter listed prices as of 22 Sept 2026, 02:49 UTC.

Nova Pro 1.0 has a published context limit of 300K tokens in the ModelCap catalogue as of 22 Sept 2026, 02:49 UTC.

Nova Pro 1.0 has 2 published OpenRouter serving endpoints, from OpenRouter as of 22 Sept 2026, 02:49 UTC.

Nova Pro 1.0 weight access is api only, from ModelCap classification of published repository metadata as of 22 Sept 2026, 02:49 UTC.

Snapshot facts · download the public dataset · methodology

ModelCap Index · Current board
21.0#185
Measured · 62% support · score interval 15.9–26.1
Evidence as of 13 Sept 2026, 00:00 UTC
Market Gravity
17.8
Secondary market signal
Input
$0.80
per 1M tokens
Output
$3.20
per 1M tokens
Context
300K
tokens
Providers
2
endpoints
Gateway spend
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
Amazon Bedrockeu-west-1Cheapest$0.80$3.20300K
Amazon Bedrock$0.80$3.20300K

ModelCap Index · Current board

Methodology
21.0
Measured · 2 public benchmark observations across 2 boards
Current board
#185
Public rank basis
Measured (measured)
Index support
61.7% · strong
Index interval
15.9–26.1
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Evidence as of
13 Sept 2026, 00:00 UTC
Identity binding
Exact catalogue product · amazon/amazon/nova-pro-v1 · aggregates disclosed benchmark configurations · endpoint configuration not claimed
Index observations used
2
Qualified Index evidence point
21.0
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
21.0
Evidence status
confirmed · 77% mass
General preference
20.9
Coding
22.4
Agents & tools
Reasoning
Evidence breadth
92%
Evidence coverage
62%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
1.8
Liquidity (providers × uptime)
35.8
Open reach (HF downloads)
Surface (context / tools / modalities)
66.2
Freshness
8.2
  • · OpenRouter popularity #291
  • · 1 live provider
  • · Catalogue: context 300000, tools, modalities Text/Image
  • · First seen 2024-12-05

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
38.8
limited · 56% metadata coverage
Not capability
Artifact reproducibility
0.0
Access & legal clarity
30.3
Deployability
74.0
Evaluation provenance
52.6

Missing: artifactReproducibility.revision-sha, artifactReproducibility.architecture-and-model-type, artifactReproducibility.parameter-count, artifactReproducibility.serialized-weight-format, artifactReproducibility.base-lineage, accessLegalClarity.declared-license, accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
17.8
OpenRouter weekly popularity
#291 of 322

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
LMArena
Official rank
#277 of 402
Rating
1290.0
95% confidence interval
1285–1295
Votes
25K
Source published at
13 Sept 2026, 00:00 UTC
Category
overall
Identity match confidence
98%

Market Gravity breakdown

Usage55%
1.8

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
35.8

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
8.2

Time since first public availability, on a six-month half-life.

Specification

Context window
300K tokens
Max output
5K tokens
Inputs
Text, Image
Outputs
Text
Tokenizer
Nova
Cached input tokens
Not offered
First seen on OpenRouter
5 Dec 2024
Knowledge cutoff
2024-10-31

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Not supported: Structured output
  • Not supported: Response format
  • Supported: Moderated

Compare Nova Pro 1.0 with

Pick any model

Benchmark leaderboards featuring Nova Pro 1.0

All leaderboards
Public benchmark boards on which Nova Pro 1.0 has a published result
LeaderboardScoreSource rankConfigurationPublished
Arena coding leaderboardArena (LMArena)13431334–1352#264 of 397Default13 Sept 2026
BFCL V4 function-calling leaderboardUC Berkeley (Gorilla)25.0#66 of 83Function calling12 Apr 2026

Alternatives to Nova Pro 1.0, by the numbers

Ranked neighbours

Models within 3 places of #185 on the ModelCap Index.

Cheaper at a similar or higher Index

Index score within 3 points of, or above, this model's, with a lower listed blended price (3:1 input:output).

Other ranked Amazon models

The same publisher's other current models with a public Index position.

Nova Pro 1.0: common questions

How does Nova Pro 1.0 rank among AI models?

Nova Pro 1.0 holds ModelCap Index position #185 of 248 ranked language models as of 22 September 2026, with an Index score of 21.0 (interval 15.9–26.1); evidence: measured. The Index combines public benchmark boards with published uncertainty; the methodology page explains the weighting.

How much does Nova Pro 1.0 cost per 1M tokens?

Nova Pro 1.0 is listed at $0.80 per 1M input tokens and $3.20 per 1M output tokens as of 22 September 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $3.20 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Nova Pro 1.0?

Nova Pro 1.0 has a published context window of 300K tokens (300,000) and a maximum output of 5K tokens. Individual providers can serve less than the published maximum; the providers table lists each endpoint's own limit.

Is Nova Pro 1.0 open-weight?

API only. No downloadable model weights are linked in the current source data; access is through a hosted API or product.

Which API providers serve Nova Pro 1.0?

One provider serves Nova Pro 1.0 through OpenRouter as of 22 September 2026: Amazon Bedrock. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

Which benchmarks has Nova Pro 1.0 been evaluated on?

Nova Pro 1.0 has published results on 2 public boards tracked by ModelCap as of 22 September 2026: Arena coding 1343 (#264 of 397) and BFCL V4 25.0 (#66 of 83). Each board page ranks every tracked model on that benchmark; the ModelCap Index combines them with published uncertainty.

How does Nova Pro 1.0 compare with Gemma SEA LION v4 4B VL?

Nova Pro 1.0 ranks #185 (Index 21.0) and Gemma SEA LION v4 4B VL ranks #186 (Index 20.9) on the ModelCap Index as of 22 September 2026. The head-to-head page lines up their benchmarks, listed prices, context windows and provider counts side by side.

When was Nova Pro 1.0 released?

Nova Pro 1.0 first appeared in the catalogue on 5 Dec 2024, with a published knowledge cutoff of 2024-10-31. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.