AmazonNova 2 Lite
Not yet ranked: too few independent results so far. Released 1 Dec 2024.
- Blended price
- $0.935/M
- $0.330 in · $2.75 out
- Output speed
- 67 tok/s
- First answer
- 0.64 s
- Context
- 1M
- Reasoning52
- Coding52
- Agents & tools40
- Human preference51
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 |
|---|---|---|
| LMArena Hard Prompts | 1358#187 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1394#176 | LMArena |
Agents & tools
| Benchmark | default | Source |
|---|---|---|
| BFCL Overall | 27.1%#59 | Berkeley Function Calling Leaderboard |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1336#194 | LMArena |
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) | 114 tok/s | 0.83 s | $0.300 | $2.50 | 1M | – |
| Amazon Bedrock | 20 tok/s | 0.45 s | $0.300 | $2.50 | 1M | – |
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. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0010 | – | 5.1 s |
| Summarise a 30-page report | 12,000 / 600 | $0.0056 | – | 9.6 s |
| Code edit | 6,000 / 1,500 | $0.0061 | – | 23.0 s |
| Agentic coding session | 60,000 / 4,000 | $0.031 | – | 1.0 min |
| Structured extraction | 2,000 / 200 | $0.0012 | – | 3.6 s |
See also
Data as of 9 Sept 2026. Compare with another model.