← Compare models
Open all in the calculator — adjust volume and token counts →
Nova 2 Lite vs Claude Haiku 4.5
List-price comparison ·Nova 2 Lite details ·Claude Haiku 4.5 details
For a typical workload (100,000 requests / mo), Nova 2 Lite is the cheapest — 57% less than the priciest here ($136.00/mo vs $320.00/mo).
| Nova 2 Lite | Claude Haiku 4.5 | |
|---|---|---|
| Input / 1M tokens | $0.300 | $1.00 |
| Output / 1M tokens | $2.50 | $5.00 |
| Typical request (1,200 in + 400 out) | $0.0014 | $0.0032 |
| Context window | 1M tokens | 200k tokens |
| Max output | 65,535 tokens | 64k tokens |
| Quality score | 68/100 | 70/100 |
| Tier | Flash | Flash |
| Provider | Amazon | Anthropic |
Projected monthly cost
| Requests / mo | Nova 2 Lite | Claude Haiku 4.5 |
|---|---|---|
| 1,000 | $1.36 | $3.20 |
| 10,000 | $13.60 | $32.00 |
| 100,000 | $136.00 | $320.00 |
Nova 2 Lite
Auto-synced from OpenRouter — no editorial write-up yet.
Claude Haiku 4.5
Very low latency for high-volume, simple tasks — classification, short summaries, and lightweight chat where response time matters more than depth.
Noticeably weaker on multi-step reasoning and long-context synthesis; pairing with a larger model for escalation is common.
More comparisons
Vendor list rates · per-request examples assume 1,200 input + 400 output tokens.