Claude Sonnet 4.5
anthropic/claude-sonnet-4.5
Compare with Claude Haiku 4.5, Claude Opus 4.5, Claude Sonnet 4.6
CompareClaude Sonnet 4.5
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Anthropicanthropic | Healthy | 100% | 99.57% | 1.60s | 18.6s | 38 tps | 1.0M | $3.00 / $15.00 |
Googlegoogle-vertex/global | Healthy | 100% | 99.90% | 1.18s | 3.96s | 35 tps | 1.0M | $3.00 / $15.00 |
Amazon Bedrockamazon-bedrock | Healthy | 99.90% | 99.87% | 2.13s | 11.1s | 32 tps | 1.0M | $3.00 / $15.00 |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 2.19s | 4.17s | 48 tps | 1.0M | $3.30 / $16.50 |
Azureazure/global | No data | — | 99.64% | 3.22s | 10.7s | 40 tps | 200K | $3.00 / $15.00 |
Claude Platform on AWSclaude-on-aws | No data | — | 76.75% | 1.94s | 1.94s | 40 tps | 1.0M | $3.00 / $15.00 |
Googlegoogle-vertex/us-east5 | No data | — | — | — | — | — | 1.0M | $3.30 / $16.50 |
- Anthropic100%Healthy24h 99.57%
- p50
- 1.60s
- p99
- 18.6s
- Throughput
- 38 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
anthropic - Google100%Healthy24h 99.90%
- p50
- 1.18s
- p99
- 3.96s
- Throughput
- 35 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
google-vertex/global - Amazon Bedrock99.90%Healthy24h 99.87%
- p50
- 2.13s
- p99
- 11.1s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
amazon-bedrock - Amazon Bedrock—No data24h 100%
- p50
- 2.19s
- p99
- 4.17s
- Throughput
- 48 tps
- Context
- 1.0M
- $/Mtok
- $3.30 / $16.50
amazon-bedrock/eu-west-1 - Azure—No data24h 99.64%
- p50
- 3.22s
- p99
- 10.7s
- Throughput
- 40 tps
- Context
- 200K
- $/Mtok
- $3.00 / $15.00
azure/global - Claude Platform on AWS—No data24h 76.75%
- p50
- 1.94s
- p99
- 1.94s
- Throughput
- 40 tps
- Context
- 1.0M
- $/Mtok
- $3.00 / $15.00
claude-on-aws - Google—No data24h —
- 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.
History
4 endpoints reporting no data are omitted from the charts.
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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.