Skip to content

Amazon · Model profile

Nova Micro

Intelligence, Performance & Price Analysis

Source: Canonical slug: nova-micro · Canonical model registry at build time

Routing verdict

Budget-friendly / task-specific model

Best for high-volume, simple, or domain-specific tasks where cost or speed matters more than deep reasoning.

Nova Micro summary metrics

Intelligence
5 scoreNova Micro scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other non-reasoning models in a similar price tier (median: 5).
Speed
331.6 output tokens/secNova Micro generates output at 331.6 tokens per second (based on Amazon's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s).
Latency
1.09s TTFTNova Micro has a time to first token (TTFT) of 1.09s (based on Amazon's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.01s).
Input Price
$0.04 / 1M tokensNova Micro costs $0.04 per 1M input tokens (very competitive, median: $0.05) and $0.14 per 1M output tokens (better than average, median: $0.20), based on Amazon's API.
Output Price
$0.14 / 1M tokensNova Micro costs $0.04 per 1M input tokens (very competitive, median: $0.05) and $0.14 per 1M output tokens (better than average, median: $0.20), based on Amazon's API.

Assessment

Routing verdict and task fit

Nova Micro scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other non-reasoning models in a similar price tier (median: 5). Nova Micro generates output at 331.6 tokens per second (based on Amazon's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s). Nova Micro costs $0.04 per 1M input tokens (very competitive, median: $0.05) and $0.14 per 1M output tokens (better than average, median: $0.20), based on Amazon's API.
Task fit assessment
WorkloadRatingNotes
Complex reasoning & agentic workflowsSuboptimalIntelligence score 5 is better suited for straightforward tasks than multi-step reasoning.
High-volume chat & customer-facingOptimalOutput speed 331.6 tokens/sec is adequate for chat.
Latency-sensitive applicationsOptimalTTFT 1.09s — adequate latency for most interactive use cases.
Cost-sensitive pipelinesOptimalOutput pricing at $0.14 is very competitive for high-volume workloads.

Evidence

Evidence charts

14 published comparison charts for this profile. Nova Micro is marked with a diamond and bold label; each chart has a table view and lists its source and retrieval date.

AA-Omniscience Index

AA-Omniscience Index (higher is better) measures knowledge reliability and hallucination. It rewards correct answers, penalizes hallucinations, and has no penalty for refusing to answer. Scores range from -100 to 100, where 0 means as many correct as incorrect answers, and negative scores mean more incorrect than correct. · Evaluation results measured independently by Artificial Analysis

19 models in the published order. Nova Micro: -48.7, row 13 of 19 in the published order.
  1. Claude Fable 5 (with fallback)40.1
  2. Gemini 3.5 Flash22.7
  3. GPT-5.5 (xhigh)20.1
  4. Grok 4.3 (high)18.3
  5. Kimi K2.66.4
  6. Muse Spark4.1
  7. GLM-5.2 (max)4
  8. MiniMax-M31.4
  9. Nemotron 3 Ultra-0.833
  10. DeepSeek V4 Pro (max)-10
  11. Llama 3.1 8B-30.3
  12. Devstral 2-46.2
  13. Nova Micro (this model)-48.7
  14. gpt-oss-120b (high)-50
  15. Devstral Small 2-56.7
  16. Phi-4 Mini-61
  17. Ministral 3 3B-64.1
  18. Gemma 3 27B-65.9
  19. Gemma 3 12B-77

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Artificial Analysis Intelligence Index by Open Weights / Proprietary

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis

19 models in the published order. Nova Micro: 4.7, row 19 of 19 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. gpt-oss-120b (high)23.8
  12. Devstral 219.2
  13. Devstral Small 217.4
  14. Llama 3.1 8B7.6
  15. Gemma 3 27B7.4
  16. Ministral 3 3B6.8
  17. Phi-4 Mini6
  18. Gemma 3 12B5.5
  19. Nova Micro (this model)4.7

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Artificial Analysis Intelligence Index

Artificial Analysis Intelligence Index v4.1 incorporates 9 evaluations: GDPval-AA v2, 𝜏³-Banking, Terminal-Bench v2.1, SciCode, Humanity's Last Exam, GPQA Diamond, CritPt, AA-Omniscience, AA-LCR · Evaluation results measured independently by Artificial Analysis

19 models in the published order. Nova Micro: 4.7, row 19 of 19 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. gpt-oss-120b (high)23.8
  12. Devstral 219.2
  13. Devstral Small 217.4
  14. Llama 3.1 8B7.6
  15. Gemma 3 27B7.4
  16. Ministral 3 3B6.8
  17. Phi-4 Mini6
  18. Gemma 3 12B5.5
  19. Nova Micro (this model)4.7

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Intelligence

Artificial Analysis Intelligence Index · Higher is better · Evaluation results measured independently by Artificial Analysis

12 models in the published order. Nova Micro: 4.7, row 12 of 12 in the published order.
  1. Claude Fable 5 (with fallback)59.9
  2. GPT-5.5 (xhigh)54.8
  3. GLM-5.2 (max)51.1
  4. Gemini 3.5 Flash50.2
  5. MiniMax-M344.4
  6. DeepSeek V4 Pro (max)44.3
  7. Kimi K2.644.2
  8. Muse Spark43.1
  9. Nemotron 3 Ultra37.8
  10. Grok 4.3 (high)37.6
  11. gpt-oss-120b (high)23.8
  12. Nova Micro (this model)4.7

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Output Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

16 models in the published order. Nova Micro: 332 t/s, row 1 of 16 in the published order.
  1. Nova Micro (this model)332 t/s
  2. gpt-oss-120b (high)314 t/s
  3. Nemotron 3 Ultra250 t/s
  4. GLM-5.2 (max)218 t/s
  5. Gemini 3.5 Flash192 t/s
  6. Ministral 3 3B178 t/s
  7. Grok 4.3 (high)164 t/s
  8. Llama 3.1 8B144 t/s
  9. MiniMax-M399 t/s
  10. GPT-5.5 (xhigh)88 t/s
  11. Devstral 276 t/s
  12. Kimi K2.676 t/s
  13. DeepSeek V4 Pro (max)72 t/s
  14. Claude Fable 5 (with fallback)71 t/s
  15. Devstral Small 268 t/s
  16. Phi-4 Mini44 t/s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Output speed context
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.

Speed

Output tokens per second · Higher is better · Evaluation results measured independently by Artificial Analysis

11 models in the published order. Nova Micro: 332 t/s, row 1 of 11 in the published order.
  1. Nova Micro (this model)332 t/s
  2. gpt-oss-120b (high)314 t/s
  3. Nemotron 3 Ultra250 t/s
  4. GLM-5.2 (max)218 t/s
  5. Gemini 3.5 Flash192 t/s
  6. Grok 4.3 (high)164 t/s
  7. MiniMax-M399 t/s
  8. GPT-5.5 (xhigh)88 t/s
  9. Kimi K2.676 t/s
  10. DeepSeek V4 Pro (max)72 t/s
  11. Claude Fable 5 (with fallback)71 t/s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Output speed context
Speed should be read together with latency and cost; fast output does not always mean better user-perceived performance.

End-to-End Response Time

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · Evaluation results measured independently by Artificial Analysis

16 models in the published order. Nova Micro: 1.51 s, row 1 of 16 in the published order.
  1. Nova Micro (this model)1.51 s
  2. Ministral 3 3B2.81 s
  3. Llama 3.1 8B3.48 s
  4. Devstral 26.55 s
  5. Devstral Small 27.37 s
  6. gpt-oss-120b (high)1.59 s
  7. Nemotron 3 Ultra2 s
  8. Phi-4 Mini11.44 s
  9. GLM-5.2 (max)2.3 s
  10. Grok 4.3 (high)3.05 s
  11. MiniMax-M35.05 s
  12. Gemini 3.5 Flash2.6 s
  13. Kimi K2.66.56 s
  14. DeepSeek V4 Pro (max)6.97 s
  15. GPT-5.5 (xhigh)5.68 s
  16. Claude Fable 5 (with fallback)7.07 s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Latency: Time To First Answer Token

Seconds to first answer token received · Accounts for reasoning model 'thinking' time · Evaluation results measured independently by Artificial Analysis

16 models in the published order. Nova Micro: 0 s, row 4 of 16 in the published order.
  1. Ministral 3 3B0 s
  2. Phi-4 Mini0 s
  3. Llama 3.1 8B0 s
  4. Nova Micro (this model)0 s
  5. Devstral Small 20 s
  6. Devstral 20 s
  7. gpt-oss-120b (high)6.37 s
  8. Nemotron 3 Ultra9.09 s
  9. GLM-5.2 (max)9.19 s
  10. Grok 4.3 (high)0 s
  11. MiniMax-M320.19 s
  12. Gemini 3.5 Flash0 s
  13. Kimi K2.658.43 s
  14. DeepSeek V4 Pro (max)60.99 s
  15. GPT-5.5 (xhigh)0 s
  16. Claude Fable 5 (with fallback)0 s

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Latency considerations
Latency includes thinking / reasoning time when applicable. Lower is better for interactive use cases.

Context Window

Context window: tokens limit · Higher is better · Evaluation results measured independently by Artificial Analysis

19 models in the published order. Nova Micro: 130k, row 15 of 19 in the published order.
  1. Gemini 3.5 Flash1M
  2. Claude Fable 5 (with fallback)1M
  3. GLM-5.2 (max)1M
  4. DeepSeek V4 Pro (max)1M
  5. Grok 4.3 (high)1M
  6. MiniMax-M31M
  7. GPT-5.5 (xhigh)922k
  8. Nemotron 3 Ultra262.1k
  9. Muse Spark262.1k
  10. Kimi K2.6256k
  11. Devstral 2256k
  12. Devstral Small 2256k
  13. Ministral 3 3B256k
  14. gpt-oss-120b (high)131.1k
  15. Nova Micro (this model)130k
  16. Llama 3.1 8B128k
  17. Gemma 3 27B128k
  18. Phi-4 Mini128k
  19. Gemma 3 12B128k

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Context window sizing
Larger context windows enable complex multi-turn tasks but may increase latency and cost for long inputs.

Cost per Intelligence Index Task

Weighted average cost (USD) per Artificial Analysis Intelligence Index task, segmented by token type. Lower is better · Evaluation results measured independently by Artificial Analysis

11 models in the published order. Nova Micro is not marked in this published set of 11 models.
  1. DeepSeek V4 Pro (max)0.0063
  2. gpt-oss-120b (high)0.00454
  3. MiniMax-M30.0139
  4. Ministral 3 3B0.00204
  5. Grok 4.3 (high)0.0101
  6. Nemotron 3 Ultra0.0209
  7. Kimi K2.60.0216
  8. GLM-5.2 (max)0.0268
  9. Gemini 3.5 Flash0.0884
  10. GPT-5.5 (xhigh)0.107
  11. Claude Fable 5 (with fallback)0.367

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Cost per Task

Weighted average cost (USD) per Intelligence Index task · Lower is better · Evaluation results measured independently by Artificial Analysis

10 models in the published order. Nova Micro is not marked in this published set of 10 models.
  1. DeepSeek V4 Pro (max)$0.045
  2. gpt-oss-120b (high)$0.061
  3. MiniMax-M3$0.125
  4. Grok 4.3 (high)$0.139
  5. Nemotron 3 Ultra$0.244
  6. Kimi K2.6$0.346
  7. GLM-5.2 (max)$0.370
  8. Gemini 3.5 Flash$0.586
  9. GPT-5.5 (xhigh)$0.863
  10. Claude Fable 5 (with fallback)$2.75

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Cost to Run Artificial Analysis Intelligence Index

Cost (USD) to run all evaluations in the Artificial Analysis Intelligence Index · Evaluation results measured independently by Artificial Analysis

11 models in the published order. Nova Micro is not marked in this published set of 11 models.
  1. Ministral 3 3B2.7
  2. gpt-oss-120b (high)3.5
  3. DeepSeek V4 Pro (max)7.2
  4. MiniMax-M314.5
  5. Grok 4.3 (high)12.5
  6. Nemotron 3 Ultra33.5
  7. GLM-5.2 (max)32.9
  8. Kimi K2.625
  9. Gemini 3.5 Flash114
  10. GPT-5.5 (xhigh)131.8
  11. Claude Fable 5 (with fallback)507.6

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.
Cost pressure
Ethen Gateway should route away from this model when the task is simple, repetitive, or likely to generate many output tokens.

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Evaluation results measured independently by Artificial Analysis

13 models; segments: Input, Output, Cache Hit. Nova Micro: $0.184, row 2 of 13 in the published order.
  • Input
  • Output
  • Cache Hit
  1. Llama 3.1 8B$0.170
  2. Nova Micro (this model)$0.184
  3. Ministral 3 3B$0.200
  4. gpt-oss-120b (high)$0.900
  5. DeepSeek V4 Pro (max)$1.31
  6. MiniMax-M3$1.56
  7. Nemotron 3 Ultra$3.60
  8. Grok 4.3 (high)$3.95
  9. Kimi K2.6$5.11
  10. GLM-5.2 (max)$6.06
  11. Gemini 3.5 Flash$10.65
  12. GPT-5.5 (xhigh)$35.50
  13. Claude Fable 5 (with fallback)$61.00

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Chart interpretation
Each bar is one model measured the same way, so this model can be read against the others. The chart lists its source and retrieval date.

Time per Intelligence Index Task

Weighted average decode time (minutes) per task; excludes TTFT and overhead time · Lower is better · Evaluation results measured independently by Artificial Analysis

14 models in the published order. Nova Micro is not marked in this published set of 14 models.
  1. Devstral 21.3
  2. Nemotron 3 Ultra1.4
  3. Devstral Small 21.4
  4. Grok 4.3 (high)1.6
  5. Ministral 3 3B1.8
  6. gpt-oss-120b (high)1.9
  7. Gemini 3.5 Flash2.2
  8. GLM-5.2 (max)2.8
  9. GPT-5.5 (xhigh)3
  10. MiniMax-M33.9
  11. Claude Fable 5 (with fallback)4.8
  12. DeepSeek V4 Pro (max)6.8
  13. Kimi K2.68.2
  14. Phi-4 Mini10.7

Published benchmark dataset · Retrieved

Method and source
Methodology
Independent test run by Artificial Analysis on dedicated hardware.
Benchmark interpretation
Higher values indicate stronger overall capability. Bars show how models compare on composite intelligence metrics.

Specifications

Architecture and limits

Nova Micro technical specifications
SpecificationValueSource
Model typeProprietaryfaq
ReasoningNofaq
Input modalitiesNova Micro supports text only input.faq
Output modalitiesNova Micro supports text only output.faq
Context window130k tokensfaq
Open weights / sourceNo, Nova Micro is proprietary. The model weights are not publicly available.faq
ParametersNova Micro is a proprietary model and Amazon has not disclosed the model size or parameter count.faq
API availabilityYes, Nova Micro is available via API through 1 provider.faq

Method

Methodology & Provenance

This page is rendered from the normalized profile and page JSON for Nova Micro.

Benchmark values are preserved as normalized; only layout, disclosure ordering, and typography are adjusted for readability.

Questions

Model FAQ and technical disclosures

Nova Micro was released on December 3, 2024.

Nova Micro was created by Amazon.

Nova Micro scores 5 (estimated) on the Artificial Analysis Intelligence Index, placing it below average among other non-reasoning models in a similar price tier (median: 5).

Nova Micro generates output at 331.6 tokens per second (based on Amazon's API), which is well above average compared to other non-reasoning models in a similar price tier (median: 121.7 t/s).

Nova Micro has a time to first token (TTFT) of 1.09s (based on Amazon's API), which is somewhat higher than average compared to other non-reasoning models in a similar price tier (median: 1.01s).

Nova Micro costs $0.04 per 1M input tokens (very competitive, median: $0.05) and $0.14 per 1M output tokens (better than average, median: $0.20), based on Amazon's API.

Nova Micro costs $0.04 per 1M input tokens and $0.14 per 1M output tokens (based on Amazon's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.03 per 1M tokens. Pricing may vary by provider.

No, Nova Micro is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.

Nova Micro supports text only input.

Nova Micro supports text only output.

No, Nova Micro does not support image input. It can only process text.

No, Nova Micro is not multimodal. It only supports text only input.

Nova Micro has a context window of 130k tokens. This determines how much text and conversation history the model can process in a single request.

No, Nova Micro is proprietary. The model weights are not publicly available.

Nova Micro is a proprietary model and Amazon has not disclosed the model size or parameter count.

Nova Micro achieves a score of 5 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Nova Micro is available via API through 1 provider.

Nova Micro is available through 1 API provider.

Models

  • 01AmazonOther Amazon models in the catalog.
  • 02LeaderboardsCertified metric ranks, when published.