Claude Opus 4.5: 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) | 99.32% | 99.61% | 99.61% | 1.62s | 4.81s | 37 tps | 200K | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.73% | 99.88% | 99.88% | 1.43s | 5.92s | 42 tps | 200K | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.60s | 3.86s | 42 tps | 200K | $5.50 / $27.50 |
Anthropicanthropic | No data | — | 99.96% | 99.87% | 99.87% | 1.82s | 7.57s | 38 tps | 200K | $5.00 / $25.00◆ (best) |
Azureazure/global | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.33s◆ (best) | 1.71s◆ (best) | 70 tps◆ (best) | 200K | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | No data | — | 97.38% | 100%◆ (best) | 100%◆ (best) | 7.03s | 7.03s | 31 tps | 200K | $5.00 / $25.00◆ (best) |
- Amazon Bedrock100%◆ (best)Healthy24h 99.32%
- 7d
- 99.61%
- 30d
- 99.61%
- p50
- 1.62s
- p99
- 4.81s
- Throughput
- 37 tps
- Context
- 200K
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - Google100%◆ (best)Healthy24h 99.73%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 1.43s
- p99
- 5.92s
- Throughput
- 42 tps
- Context
- 200K
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.60s
- p99
- 3.86s
- Throughput
- 42 tps
- Context
- 200K
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/eu-west-1 - No data24h 99.96%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 1.82s
- p99
- 7.57s
- Throughput
- 38 tps
- Context
- 200K
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.33s◆ (best)
- p99
- 1.71s◆ (best)
- Throughput
- 70 tps◆ (best)
- Context
- 200K
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/global - No data24h 97.38%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 7.03s
- p99
- 7.03s
- Throughput
- 31 tps
- Context
- 200K
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws
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, averaged over the hour.
Throughput
Median tokens per second.