Claude Opus 4.1: 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 | — | 99.84% | 99.74% | 99.74% | 3.73s | 35.2s | 2.0 tps | 200K | $15.00 / $75.00◆ (best) |
Googlegoogle-vertex/global | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 2.17s◆ (best) | 2.94s◆ (best) | 18 tps◆ (best) | 200K | $15.00 / $75.00◆ (best) |
- No data24h 99.84%
- 7d
- 99.74%
- 30d
- 99.74%
- p50
- 3.73s
- p99
- 35.2s
- Throughput
- 2.0 tps
- Context
- 200K
- $/Mtok
- $15.00 / $75.00◆ (best)
amazon-bedrock - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.17s◆ (best)
- p99
- 2.94s◆ (best)
- Throughput
- 18 tps◆ (best)
- Context
- 200K
- $/Mtok
- $15.00 / $75.00◆ (best)
google-vertex/global
Measured 2m 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.