Nova 2 Lite: providers compared
Every endpoint serving this model, side by side. ◆ marks the best value in each column — per model, never fleet-wide.
Current state
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Amazon Bedrockamazon-bedrock | Healthy | 100%◆ (best) | 82.90% | 98.34%◆ (best) | 99.39%◆ (best) | 489ms | 3.00s | 116 tps | 1.0M | $0.300 / $2.50◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | Healthy | 100%◆ (best) | 78.56% | 97.87% | 99.31% | 362ms◆ (best) | 1.78s◆ (best) | 120 tps◆ (best) | 1.0M | $0.300 / $2.50◆ (best) |
- Amazon Bedrock100%◆ (best)Healthy24h 82.90%
- 7d
- 98.34%◆ (best)
- 30d
- 99.39%◆ (best)
- p50
- 489ms
- p99
- 3.00s
- Throughput
- 116 tps
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50◆ (best)
amazon-bedrock - Amazon Bedrock100%◆ (best)Healthy24h 78.56%
- 7d
- 97.87%
- 30d
- 99.31%
- p50
- 362ms◆ (best)
- p99
- 1.78s◆ (best)
- Throughput
- 120 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.300 / $2.50◆ (best)
amazon-bedrock/eu-west-1
Measured 44s ago. Latency and throughput are OpenRouter's rolling 30-minute windows. ◆ marks the best value in each column among these endpoints.
Price vs latency
One dot per endpoint at the latest round · further left = faster, lower = cheaper · hover a dot for its tag
History
Availability
Axis starts at 90% so small differences stay visible; it expands to 0 when an endpoint falls below.
Time to first token
Logarithmic axis — the fleet spans two orders of magnitude. P50 is OpenRouter's rolling 30-minute window, averaged over the hour.
Throughput
Median tokens per second.