Claude Sonnet 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/global | Healthy | 100%◆ (best) | 99.98% | 99.87% | 99.87% | 2.29s | 6.54s | 57 tps | 1.0M | $2.00 / $10.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.98% | 99.98% | 99.98% | 4.40s | 13.6s | 56 tps | 1.0M | $2.00 / $10.00◆ (best) |
Azureazure/global | Healthy | 100%◆ (best) | 99.50% | 99.82% | 99.82% | 2.47s | 6.62s | 64 tps | 1.0M | $2.00 / $10.00◆ (best) |
Azureazure/us | Healthy | 100%◆ (best) | 99.96% | 99.97% | 99.97% | 814ms◆ (best) | 5.57s◆ (best) | 72 tps | 1.0M | $2.00 / $10.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.94% | 99.94% | 99.94% | 1.80s | 7.31s | 28 tps | 1.0M | $2.00 / $10.00◆ (best) |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $2.20 / $11.00 |
Googlegoogle-vertex/europe | No data | — | 99.99% | 99.98% | 99.98% | 3.88s | 6.87s | 96 tps◆ (best) | 1.0M | $2.20 / $11.00 |
Googlegoogle-vertex/global | No data | — | 99.93% | 99.91% | 99.91% | 2.31s | 6.72s | 64 tps | 1.0M | $2.00 / $10.00◆ (best) |
Googlegoogle-vertex/us | No data | — | — | — | — | — | — | — | 1.0M | $2.20 / $11.00 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.98%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 2.29s
- p99
- 6.54s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
amazon-bedrock/global - Anthropic100%◆ (best)Healthy24h 99.98%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 4.40s
- p99
- 13.6s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
anthropic - Azure100%◆ (best)Healthy24h 99.50%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 2.47s
- p99
- 6.62s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
azure/global - Azure100%◆ (best)Healthy24h 99.96%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 814ms◆ (best)
- p99
- 5.57s◆ (best)
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
azure/us - Claude Platform on AWS100%◆ (best)Healthy24h 99.94%
- 7d
- 99.94%
- 30d
- 99.94%
- p50
- 1.80s
- p99
- 7.31s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
claude-on-aws - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
amazon-bedrock/us-east-1 - No data24h 99.99%
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- 3.88s
- p99
- 6.87s
- Throughput
- 96 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/europe - No data24h 99.93%
- 7d
- 99.91%
- 30d
- 99.91%
- p50
- 2.31s
- p99
- 6.72s
- Throughput
- 64 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
google-vertex/global - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/us
Measured 3m 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.