Claude Sonnet 4.6: 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) | 99.96% | 99.95% | 99.95% | 1.38s | 6.27s | 41 tps | 1.0M | $3.00 / $15.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.91% | 99.90% | 99.90% | 1.05s◆ (best) | 3.07s | 37 tps | 1.0M | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.97% | 99.96%◆ (best) | 99.96%◆ (best) | 1.57s | 6.37s | 39 tps | 1.0M | $3.00 / $15.00◆ (best) |
Anthropicanthropic | Healthy | 99.72% | 99.90% | 99.85% | 99.85% | 1.76s | 12.5s | 36 tps | 1.0M | $3.00 / $15.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | — | — | — | — | — | — | 1.0M | $3.30 / $16.50 |
Amazon Bedrockamazon-bedrock/us | No data | — | — | — | — | — | — | — | 1.0M | $3.30 / $16.50 |
Azureazure/global | No data | — | 100% | 99.75% | 99.75% | 1.76s | 5.24s | 49 tps◆ (best) | 1.0M | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | 99.83% | 99.52% | 99.52% | 1.56s | 2.55s | 38 tps | 1.0M | $3.30 / $16.50 |
Googlegoogle-vertex/us-east5 | No data | — | 100% | — | — | 1.11s | 1.26s◆ (best) | 14 tps | 1.0M | $3.30 / $16.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.96%
- 7d
- 99.95%
- 30d
- 99.95%
- p50
- 1.38s
- p99
- 6.27s
- Throughput
- 41 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
amazon-bedrock/global - Claude Platform on AWS100%◆ (best)Healthy24h 99.91%
- 7d
- 99.90%
- 30d
- 99.90%
- p50
- 1.05s◆ (best)
- p99
- 3.07s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
claude-on-aws - Google100%◆ (best)Healthy24h 99.97%
- 7d
- 99.96%◆ (best)
- 30d
- 99.96%◆ (best)
- p50
- 1.57s
- p99
- 6.37s
- Throughput
- 39 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
google-vertex/global - Anthropic99.72%Healthy24h 99.90%
- 7d
- 99.85%
- 30d
- 99.85%
- p50
- 1.76s
- p99
- 12.5s
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
anthropic - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
amazon-bedrock/eu-west-1 - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
amazon-bedrock/us - No data24h 100%
- 7d
- 99.75%
- 30d
- 99.75%
- p50
- 1.76s
- p99
- 5.24s
- Throughput
- 49 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
azure/global - No data24h 99.83%
- 7d
- 99.52%
- 30d
- 99.52%
- p50
- 1.56s
- p99
- 2.55s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
google-vertex/europe - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 1.11s
- p99
- 1.26s◆ (best)
- Throughput
- 14 tps
- 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.
Throughput
Median tokens per second.