AmazonAuto-detectedAmazon Nova Lite
Best configuration ranks #529 of 610 on the BenchLeader Index at 39.4 ±4.1. Last measured 2 Sept 2026. Released 3 Dec 2024.
- Blended price
- $0.105/M
- $0.060 in · $0.240 out
- Output speed
- 171 tok/s
- First answer
- 0.93 s
- first token 3.67 s
- Context
- 300k
- Overall index39
- Reasoning36
- Coding42
- Agents & tools34
- Knowledge44
- Instruction following37
- Human preference41
- Multimodal24
- Long context35
- Composite37
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| Humanity's Last Exam | 3.6%#43 | Scale AI / CAIS |
| LMArena Hard Prompts | 1271#257 | LMArena |
| GPQA Diamond (AA)not in index | 43.3%#434 | Artificial Analysis |
| Humanity's Last Exam (AA)not in index | 4.3%#433 | Artificial Analysis |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1306#252 | LMArena |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| Terminal-Bench Hard | 0.8%#332 | Artificial Analysis |
| τ²-Bench Telecom (AA)not in index | 17.5%#335 | Artificial Analysis |
Knowledge
| Benchmark | default | Source |
|---|---|---|
| AA-Omniscience | -42.2#266 | Artificial Analysis |
Instruction following
| Benchmark | default | Source |
|---|---|---|
| IFBench | 34.1%#307 | Artificial Analysis |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1260#262 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 990#126 | LMArena |
| MMMU-Pro | 37.8%#234 | Artificial Analysis |
| VISTA | 25.5%#54 | Scale AI SEAL |
Long context
| Benchmark | default | Source |
|---|---|---|
| AA-LCR | 19.0%#368 | Artificial Analysis |
Composite
| Benchmark | default | Source |
|---|---|---|
| AA Intelligence Index | 6.7#431 | Artificial Analysis |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| Amazon Bedrock (EU) | 39 tok/s | 4.91 s | $0.060 | $0.240 | 300k | – |
| Amazon Bedrock | 19 tok/s | 2.44 s | $0.060 | $0.240 | 300k | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.015 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0001 | $0.0001 | 2.7 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0009 | $0.0005 | 4.4 s |
| Code edit | 6,000 / 1,500 | $0.0007 | $0.0005 | 9.7 s |
| Agentic coding session | 60,000 / 4,000 | $0.0046 | $0.0025 | 24.3 s |
| Structured extraction | 2,000 / 200 | $0.0002 | $0.0001 | 2.1 s |
See also
Data as of 9 Sept 2026. Compare with another model.