Claude Sonnet 4: 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% | 100% | 100% | 99.99% | 1.01s | 5.09s | 58 tps | 200K | $3.00 / $15.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 200K | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex | No data | — | — | — | 9.09% | — | — | — | 1.0M | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | — | — | 100%◆ (best) | — | — | — | 1.0M | $3.00 / $15.00◆ (best) |
Googlegoogle-vertex/global | No data | — | — | — | 99.24% | — | — | — | 1.0M | $3.00 / $15.00◆ (best) |
- Amazon Bedrock100%Healthy24h 100%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 1.01s
- p99
- 5.09s
- Throughput
- 58 tps
- Context
- 200K
- $/Mtok
- $3.00 / $15.00◆ (best)
amazon-bedrock - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 200K
- $/Mtok
- $3.00 / $15.00◆ (best)
amazon-bedrock/eu-west-1 - No data24h —
- 7d
- —
- 30d
- 9.09%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
google-vertex - No data24h —
- 7d
- —
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
google-vertex/europe - No data24h —
- 7d
- —
- 30d
- 99.24%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00◆ (best)
google-vertex/global
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.