Nova Pro 1.0: 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 | No data | — | 97.71% | 99.84%◆ (best) | 99.93%◆ (best) | 613ms | 1.17s | 54 tps | 300K | $0.800 / $3.20◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 76.09% | 99.55% | 99.77% | 603ms◆ (best) | 1.09s◆ (best) | 164 tps◆ (best) | 300K | $0.800 / $3.20◆ (best) |
- No data24h 97.71%
- 7d
- 99.84%◆ (best)
- 30d
- 99.93%◆ (best)
- p50
- 613ms
- p99
- 1.17s
- Throughput
- 54 tps
- Context
- 300K
- $/Mtok
- $0.800 / $3.20◆ (best)
amazon-bedrock - No data24h 76.09%
- 7d
- 99.55%
- 30d
- 99.77%
- p50
- 603ms◆ (best)
- p99
- 1.09s◆ (best)
- Throughput
- 164 tps◆ (best)
- Context
- 300K
- $/Mtok
- $0.800 / $3.20◆ (best)
amazon-bedrock/eu-west-1
Measured 4m 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.
Throughput
Median tokens per second.