Claude Haiku 5.5: 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 | Healthy | 100%◆ (best) | 100% | 99.87% | 99.87% | 2.59s | 13.3s | 145 tps | 1.0M | $0.100 / $0.500◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 768ms◆ (best) | 5.87s | 169 tps | 1.0M | $0.110 / $0.550 |
Amazon Bedrockamazon-bedrock/us-east-1 | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 2.34s | 3.64s◆ (best) | 171 tps | 1.0M | $0.110 / $0.550 |
Anthropicanthropic | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 967ms | 9.04s | 147 tps | 1.0M | $0.100 / $0.500◆ (best) |
Azureazure/global | Healthy | 100%◆ (best) | 100% | 99.99% | 99.99% | 1.14s | 18.6s | 154 tps | 1.0M | $0.100 / $0.500◆ (best) |
Azureazure/us | Healthy | 100%◆ (best) | 100% | — | — | 1.78s | 4.10s | 205 tps◆ (best) | 1.0M | $0.110 / $0.550 |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 100% | 99.97% | 99.97% | 1.96s | 18.6s | 147 tps | 1.0M | $0.100 / $0.500◆ (best) |
Googlegoogle-vertex/europe | Healthy | 100%◆ (best) | 100% | 99.82% | 99.82% | 1.36s | 7.70s | 199 tps | 1.0M | $0.110 / $0.550 |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 916ms | 11.2s | 146 tps | 1.0M | $0.100 / $0.500◆ (best) |
Googlegoogle-vertex/us | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 1.41s | 3.70s | 193 tps | 1.0M | $0.110 / $0.550 |
- Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 99.87%
- 30d
- 99.87%
- p50
- 2.59s
- p99
- 13.3s
- Throughput
- 145 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
amazon-bedrock - Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 768ms◆ (best)
- p99
- 5.87s
- Throughput
- 169 tps
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.550
amazon-bedrock/eu-west-1 - Amazon Bedrock100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.34s
- p99
- 3.64s◆ (best)
- Throughput
- 171 tps
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.550
amazon-bedrock/us-east-1 - Anthropic100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 967ms
- p99
- 9.04s
- Throughput
- 147 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
anthropic - Azure100%◆ (best)Healthy24h 100%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.14s
- p99
- 18.6s
- Throughput
- 154 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
azure/global - Azure100%◆ (best)Healthy24h 100%
- 7d
- —
- 30d
- —
- p50
- 1.78s
- p99
- 4.10s
- Throughput
- 205 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.550
azure/us - Claude Platform on AWS100%◆ (best)Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.97%
- p50
- 1.96s
- p99
- 18.6s
- Throughput
- 147 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
claude-on-aws - Google100%◆ (best)Healthy24h 100%
- 7d
- 99.82%
- 30d
- 99.82%
- p50
- 1.36s
- p99
- 7.70s
- Throughput
- 199 tps
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.550
google-vertex/europe - Google100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 916ms
- p99
- 11.2s
- Throughput
- 146 tps
- Context
- 1.0M
- $/Mtok
- $0.100 / $0.500◆ (best)
google-vertex/global - Google100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.41s
- p99
- 3.70s
- Throughput
- 193 tps
- Context
- 1.0M
- $/Mtok
- $0.110 / $0.550
google-vertex/us
Measured 4m 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.