Skip to content

Amazon · Chat

Nova Micro

Amazon 🇺🇸ChatNova familyOne of its sources says the weights aren't publicly available.
From Neosantara's listing:
Amazon Nova Micro is the most affordable model with 300K context. Great for text generation and function calling.
llminfo IQ
103.3
Max context
300K
Listings
28

Evidence and sources

llminfo IQ 103.3, ranked among chat models. From 102 benchmarks. Plenty of data behind it.How llminfo IQ is computedPoor value (47.4). Costs more per task than its benchmark results predict. From 2 benchmarks with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 3 Dec 2024 Training-data cutoff, as its sources state it Maker HQ: US (according to Amazon Web Services's own website)
All rankings: #182 on OpenRouter today #193 on OpenRouter this week #200 on OpenRouter this monthSources: AWS Bedrock Runtime data, Models.dev data, AI/ML API data, OpenRouter data docs, Neosantara Inference data, llminfo researchPrimary data from AWS Bedrock Runtime from Models.dev: weights availability from AI/ML API: primary mode from OpenRouter: knowledge cutoff from Neosantara Inference: description from llminfo research: release date
Tags from its sources:instructtoolsvisionproprietaryfastcost-efficient

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Trade-offs

No open weights

The weights aren't public, so you can't run it yourself.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 7 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionFunction callingStructured outputPrompt cachingBatch API

Listings

 Amazon Web Servicesamazon.nova-micro-v1:0Sources: AWS Bedrock Runtime data, GenAI Prices data, LiteLLM data, Models.dev data128K$0.035cache read $0.0088batch $0.0175$0.14batch $0.07———
 302ainova-microSource: 302.ai data300K$0.035$0.14———
 Eden AIInference by Amazon Web Servicesamazon/amazon.nova-micro-v1:0Source: Models.dev data128K$0.035cache read $0.011$0.14———
 Flowdotamazon/nova-micro-v1, amazon/nova-micro-v1:0Source: FlowDot data128K$0.035$0.14———
 Kiloamazon/nova-microSources: Kilo AI Gateway data, Models.dev data128K$0.035cache read $0.0087$0.14$0.00——
 Nous Portalamazon/nova-micro-v1Source: Nous Portal Inference Gateway data128K$0.035$0.14———
 OpenRouterInference by Amazon Web Servicesamazon/nova-micro-v1 · eu-west-1Source: OpenRouter data docs128K$0.035$0.14—194357ms
 Vercelamazon/nova-microSources: Models.dev data, Vercel AI Gateway data128K$0.035cache read $0.0087$0.14———
 Neosantaraamazon-nova-microSource: Neosantara Inference data300K$0.035$0.14———
 Sap AI Coreamazon--nova-microSource: Models.dev data128K$0.035$0.14———
Show all 22 listings

Showing 10 of 22: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by Aimlapi, Cortecs AI, Eurouter, Vercel AI Gateway.

5 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Knowledge

HELM60 related benchmarks · 60 results
Show 54 more resultsHide 54 results

General

SQuALITYSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
TranslationSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Reasoning

ARC-CSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
BBHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
CRAGSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
DROPSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Math

FinQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GSM8KSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
MATHSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
GPQA Diamond3 results
Source: OpenRouter benchmark exports · Oct 2026
nova-micro-v1 · 90-day results
Across 2 providers lowest 38.6% median 63.7% highest 88.9%OpenRouter's automatic routing 88.6%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • Anthropic
  • OpenRouter's automatic routing
  • Amazon Bedrock

Agentic

BFCLSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
Source: OpenRouter benchmark exports · Oct 2026
nova-micro-v1 · 90-day results
Across 2 providers lowest 17.9% median 46% highest 74%OpenRouter's automatic routing 76.7%
Show results from 2 providers and OpenRouter's automatic routingHide results from 2 providers and OpenRouter's automatic routing
  • OpenRouter's automatic routing
  • Anthropic
  • Amazon Bedrock

Coding

HumanEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Instruction following

IFEvalSource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Factuality

Human preference

Multilingual

Other

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · OpenRouter public benchmark leaderboard and search-lane exports, CC BY 4.0. Fractional source scores converted to percentages; immutable dated snapshots. (licence) · Stanford HELM (Stanford CRFM); scenario scores from Capabilities, Safety, Long Context, MedHELM, AIR-Bench, MMLU and Finance · Stanford HELM (Stanford CRFM), Apache-2.0 (licence)

Around the web

Also known as: amazon-nova-micro, amazon-nova/nova-micro-v1, amazon.nova-micro-v1%3a0, amazon.nova-micro-v1:0, amazon.nova-micro-v1:0:128k, amazon.nova-micro-v1:0:24k, amazon/amazon.nova-micro-v1:0, amazon/amazon.nova-micro-v1:0@us, amazon/nova-micro, amazon/nova-micro-v1, amazon/nova-micro-v1:0, apac.amazon.nova-micro-v1:0, bedrock/ap-northeast-1/amazon.nova-micro-v1:0, bedrock/ap-northeast-2/amazon.nova-micro-v1:0, bedrock/ap-south-1/amazon.nova-micro-v1:0, bedrock/ap-southeast-1/amazon.nova-micro-v1:0, bedrock/ap-southeast-2/amazon.nova-micro-v1:0, bedrock/eu-central-1/amazon.nova-micro-v1:0, bedrock/eu-north-1/amazon.nova-micro-v1:0, bedrock/eu-north-1/eu.amazon.nova-micro-v1:0, bedrock/eu-south-1/amazon.nova-micro-v1:0, bedrock/eu-south-1/eu.amazon.nova-micro-v1:0, bedrock/eu-south-2/amazon.nova-micro-v1:0, bedrock/eu-south-2/eu.amazon.nova-micro-v1:0, bedrock/eu-west-1/amazon.nova-micro-v1:0, bedrock/eu-west-1/eu.amazon.nova-micro-v1:0, bedrock/eu-west-2/amazon.nova-micro-v1:0, bedrock/eu-west-3/amazon.nova-micro-v1:0, bedrock/eu-west-3/eu.amazon.nova-micro-v1:0, bedrock/il-central-1/amazon.nova-micro-v1:0, bedrock/me-central-1/amazon.nova-micro-v1:0, bedrock/us-east-1/amazon.nova-micro-v1:0, bedrock/us-east-2/amazon.nova-micro-v1:0, bedrock/us-gov-west-1/amazon.nova-micro-v1:0, bedrock/us-west-2/amazon.nova-micro-v1:0, eu.amazon.nova-micro-v1%3a0, eu.amazon.nova-micro-v1:0, nova-micro-v1, us.amazon.nova-micro-v1%3a0, us.amazon.nova-micro-v1:0, vercel_ai_gateway/amazon/nova-micro

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works