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) | 99.99% | 99.95% | 99.93% | 1.61s | 12.1s | 67 tps | 1.0M | $2.00 / $10.00◆ (best) |
Googlegoogle-vertex/europe | Healthy | 100%◆ (best) | 99.97% | 99.96% | 99.96% | 2.20s | 8.34s | 102 tps◆ (best) | 1.0M | $2.20 / $11.00 |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.99% | 99.99% | 99.95% | 1.03s | 17.2s | 81 tps | 1.0M | $2.00 / $10.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 99.99% | 99.99% | 99.98% | 99.91% | 1.96s | 15.3s | 65 tps | 1.0M | $2.00 / $10.00◆ (best) |
Anthropicanthropic | Healthy | 99.86% | 99.99% | 99.99% | 99.96% | 1.45s | 8.23s | 75 tps | 1.0M | $2.00 / $10.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 99.75% | 1.59s | 4.56s | 67 tps | 1.0M | $2.20 / $11.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 99.91% | 99.96% | — | — | — | 1.0M | $2.20 / $11.00 |
Azureazure/global | No data | — | 99.85% | 99.92% | 99.74% | 1.60s | 4.91s | 73 tps | 1.0M | $2.00 / $10.00◆ (best) |
Azureazure/us | No data | — | — | 100%◆ (best) | 99.98% | — | — | — | 1.0M | $2.20 / $11.00 |
Googlegoogle-vertex/us | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 978ms◆ (best) | 1.21s◆ (best) | 63 tps | 1.0M | $2.20 / $11.00 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.99%
- 7d
- 99.95%
- 30d
- 99.93%
- p50
- 1.61s
- p99
- 12.1s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
amazon-bedrock/global - Google100%◆ (best)Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 2.20s
- p99
- 8.34s
- Throughput
- 102 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/europe - Google100%◆ (best)Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.95%
- p50
- 1.03s
- p99
- 17.2s
- Throughput
- 81 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
google-vertex/global - Claude Platform on AWS99.99%Healthy24h 99.99%
- 7d
- 99.98%
- 30d
- 99.91%
- p50
- 1.96s
- p99
- 15.3s
- Throughput
- 65 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
claude-on-aws - Anthropic99.86%Healthy24h 99.99%
- 7d
- 99.99%
- 30d
- 99.96%
- p50
- 1.45s
- p99
- 8.23s
- Throughput
- 75 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
anthropic - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.75%
- p50
- 1.59s
- p99
- 4.56s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- 99.91%
- 30d
- 99.96%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
amazon-bedrock/us-east-1 - No data24h 99.85%
- 7d
- 99.92%
- 30d
- 99.74%
- p50
- 1.60s
- p99
- 4.91s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $10.00◆ (best)
azure/global - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 978ms◆ (best)
- p99
- 1.21s◆ (best)
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $2.20 / $11.00
google-vertex/us
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.
Throughput
Median tokens per second.