Claude Opus 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) | 99.95% | 99.96% | 99.96% | 3.10s | 7.62s | 66 tps◆ (best) | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100%◆ (best) | 99.97% | 99.98% | 99.98% | 2.19s | 5.21s◆ (best) | 50 tps | 1.0M | $5.50 / $27.50 |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.91% | 99.78% | 99.78% | 4.24s | 10.0s | 55 tps | 1.0M | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 99.90% | 99.90% | 99.92% | 99.92% | 4.22s | 9.22s | 44 tps | 1.0M | $5.00 / $25.00◆ (best) |
Azureazure/global | No data | — | 99.87% | 99.93% | 99.93% | 2.67s | 6.96s | 65 tps | 1.0M | $5.00 / $25.00◆ (best) |
Azureazure/us | No data | — | 99.93% | 99.98% | 99.98% | 2.14s◆ (best) | 7.99s | 42 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/global | No data | — | 99.95% | 99.93% | 99.93% | 3.95s | 74.5s | 57 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/us | No data | — | — | — | — | — | — | — | 1.0M | $5.50 / $27.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.95%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 3.10s
- p99
- 7.62s
- Throughput
- 66 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - Amazon Bedrock100%◆ (best)Healthy24h 99.97%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 2.19s
- p99
- 5.21s◆ (best)
- Throughput
- 50 tps
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/us-east-1 - Anthropic100%◆ (best)Healthy24h 99.91%
- 7d
- 99.78%
- 30d
- 99.78%
- p50
- 4.24s
- p99
- 10.0s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - Claude Platform on AWS99.90%Healthy24h 99.90%
- 7d
- 99.92%
- 30d
- 99.92%
- p50
- 4.22s
- p99
- 9.22s
- Throughput
- 44 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - No data24h 99.87%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 2.67s
- p99
- 6.96s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/global - No data24h 99.93%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 2.14s◆ (best)
- p99
- 7.99s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/europe - No data24h 99.95%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 3.95s
- p99
- 74.5s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/us
Measured 38s 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.