Amazon, proprietary
Nova Premier 1.0
Nova Premier 1.0 by Amazon ranks 189th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.3. Its strongest category is writing & preference, where it ranks 178th. API pricing starts at $2.50 per million input tokens and $12.50 per million output tokens, with a 1M-token context window.
Last verified
Specifications
- Noometry rank
- #189 of 354
- Index score
- 38.3
- Evidence
- Confirmed 6 results
- Provider
- Amazon
- Released
- April 30, 2025
- Weights
- Proprietary
- Reasoning
- No
- Context window
- 1M
- Max output
- 10K
- Input price
- $2.50 / M
- Output price
- $12.50 / M
- Blended price
- $5 / M
- Output speed
- 9 tokens/s Kagi
- Value
- #194 of 219
- Knowledge cutoff
- October 2024
- Input
- text, image, video, pdf
Category scores
Each category score combines every public result we have in that category.
- Reasoning 23.0
- Math 33.8
- Knowledge 35.8
- Instruction Following 66.8
- Writing & Preference 51.0
| Category | Score | Rank | Results |
|---|---|---|---|
| Reasoning | 23.0 | #185 | 1 |
| Math | 33.8 | #199 | 1 |
| Knowledge | 35.8 | #180 | 2 |
| Instruction Following | 66.8 | #204 | 1 |
| Writing & Preference | 51.0 | #178 | 1 |
Strengths and weaknesses
Categories where Nova Premier 1.0 places highest and lowest among the models ranked in each, with its score against that category's median.
Strongest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Reasoning | 23.0 | −0.6 | #185 of 350, top 53% |
| Writing & Preference | 51.0 | −2.8 | #178 of 312, top 58% |
Weakest categories
| Category | Score | vs median | Rank |
|---|---|---|---|
| Instruction Following | 66.8 | −4.5 | #204 of 305, top 67% |
| Math | 33.8 | −2.8 | #199 of 327, top 61% |
Closest competitors
The models ranked just above and below Nova Premier 1.0. When scores are this close, price and speed are often the better way to choose.
| Model | Rank | Score | Blended $/M | Speed | |
|---|---|---|---|---|---|
| Trinity Large Thinking | #185 | 38.6 | $0.39 | — | Compare |
| GPT-5.1-Codex | #186 | 38.6 | $3.44 | — | Compare |
| Sonar | #187 | 38.5 | $1 | — | Compare |
| MiniMax-M2.5 | #188 | 38.3 | $0.52 | 49 | Compare |
| Qwen3-Coder 480B-A35B Instruct | #190 | 38.1 | $3 | 67 | Compare |
| Olmo 3.1 32b Think | #191 | 37.9 | — | — | Compare |
| GPT-5-Codex | #192 | 37.9 | $3.44 | 95 | Compare |
| Hunyuan Standard 2025 02 10 | #193 | 37.9 | — | — | Compare |
Sponsored placements are available on pages like this one. Advertise on Noometry
Benchmark results
Every published result we track, with its source. Bold rows are the ones used for ranking; where several exist we prefer independent runs over self-reported numbers.
Reasoning
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Kagi LLM Benchmark | 44.8% | #71 of 99, top 72% | Kagi LLM Benchmark |
Math
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| Omni-MATH | 35% | #33 of 57, top 58% | HELM Capabilities |
Knowledge
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| MMLU-Pro | 72.6% | #31 of 58, top 54% | HELM Capabilities | ||
| GPQA (HELM) | 51.8% | #32 of 57, top 57% | HELM Capabilities |
Instruction Following
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| IFEval | 80.3% | #42 of 57, top 74% | HELM Capabilities |
Writing & Preference
| Benchmark | Score | Position | Setting | Source | Date |
|---|---|---|---|---|---|
| WildBench | 78.8% | #39 of 57, top 69% | HELM Capabilities |
API pricing by provider
| Route | Input $/M | Output $/M | Cached input $/M | Checked |
|---|---|---|---|---|
| bedrock | $2.50 | $12.50 | $0.63 | 2026-10-10 |
| openrouter | $2.50 | $12.50 | $0.63 | 2026-10-10 |
Compare Nova Premier 1.0
- Nova Premier 1.0 vs MiniMax-M2.5
- Nova Premier 1.0 vs Qwen3-Coder 480B-A35B Instruct
- Nova Premier 1.0 vs Sonar
- Nova Premier 1.0 vs Olmo 3.1 32b Think
- Nova Premier 1.0 vs GPT-5.1-Codex
- Nova Premier 1.0 vs GPT-5-Codex
- Nova Premier 1.0 vs GPT-6 Astra
- Nova Premier 1.0 vs Claude Fable 5.1
- Nova Premier 1.0 vs Gemini 3.8 Flash
- Nova Premier 1.0 vs Kimi K3
- Nova Premier 1.0 vs Grok 4.6
- Nova Premier 1.0 vs Qwen3.8 Max
- Nova Premier 1.0 vs GLM-5.3
- Nova Premier 1.0 vs Muse Spark 1.3
Frequently asked questions
How good is Nova Premier 1.0?
Nova Premier 1.0 by Amazon ranks 189th of 354 ranked models on the Noometry Index as of October 2026, with a score of 38.3. Its strongest category is writing & preference, where it ranks 178th. API pricing starts at $2.50 per million input tokens and $12.50 per million output tokens, with a 1M-token context window.
How much does Nova Premier 1.0 cost?
Nova Premier 1.0 costs $2.50 per million input tokens and $12.50 per million output tokens on bedrock, with cached input at $0.63.
What is Nova Premier 1.0's context window?
Nova Premier 1.0 accepts up to 1M tokens of input and can write up to 10K tokens in one response.
Is Nova Premier 1.0 open source?
No. Nova Premier 1.0 is proprietary and available only through Amazon's API and partner platforms.
How fast is Nova Premier 1.0?
Nova Premier 1.0 generated about 9 output tokens per second in the Kagi LLM Benchmark's timed runs. Speed varies by provider, load and reasoning effort.
What are Nova Premier 1.0's strengths and weaknesses?
Relative to other ranked models, Nova Premier 1.0 places best in reasoning, writing & preference and lowest in instruction following, math.
What is Nova Premier 1.0 best at?
Its best category is writing & preference, where it ranks 178th on Noometry.