Claude Sonnet 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) | 99.97% | 99.94% | 99.93% | 1.55s | 5.87s | 37 tps | 1.0M | $3.00 / $15.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.98% | 99.84% | 99.89% | 1.03s | 3.53s | 42 tps | 1.0M | $3.00 / $15.00◆ (best) |
Azureazure/global | Healthy | 100%◆ (best) | 99.99% | 99.97% | 99.05% | 1.42s | 3.67s | 36 tps | 200K | $3.00 / $15.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 100% | 99.82% | 99.88% | 1.36s | 10.4s | 37 tps | 1.0M | $3.00 / $15.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.31s | 1.47s◆ (best) | 43 tps◆ (best) | 1.0M | $3.30 / $16.50 |
Googlegoogle-vertex/global | No data | — | 99.81% | 99.64% | 99.76% | 966ms◆ (best) | 8.66s | 35 tps | 1.0M | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex/us-east5 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $3.30 / $16.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.97%
- 7d
- 99.94%
- 30d
- 99.93%
- p50
- 1.55s
- p99
- 5.87s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
amazon-bedrock - Anthropic100%◆ (best)Healthy24h 99.98%
- 7d
- 99.84%
- 30d
- 99.89%
- p50
- 1.03s
- p99
- 3.53s
- Throughput
- 42 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
anthropic - Azure100%◆ (best)Healthy24h 99.99%
- 7d
- 99.97%
- 30d
- 99.05%
- p50
- 1.42s
- p99
- 3.67s
- Throughput
- 36 tps
- Context
- 200K
- $/Mtok
- $3.00 / $15.00◆ (best)
azure/global - Claude Platform on AWS100%◆ (best)Healthy24h 100%
- 7d
- 99.82%
- 30d
- 99.88%
- p50
- 1.36s
- p99
- 10.4s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
claude-on-aws - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.31s
- p99
- 1.47s◆ (best)
- Throughput
- 43 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
amazon-bedrock/eu-west-1 - No data24h 99.81%
- 7d
- 99.64%
- 30d
- 99.76%
- p50
- 966ms◆ (best)
- p99
- 8.66s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
google-vertex/global - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
google-vertex/us-east5
Measured 1m 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.