Claude Haiku 4.5: 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/eu-west-1 | Healthy | 100%◆ (best) | 99.85% | 99.90% | 99.96% | 514ms | 1.04s◆ (best) | 91 tps | 200K | $1.10 / $5.50 |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.96% | 99.90% | 99.94% | 375ms◆ (best) | 1.64s | 90 tps | 200K | $1.00 / $5.00◆ (best) |
Azureazure/global | Healthy | 100%◆ (best) | 99.90% | 99.77% | 99.89% | 491ms | 3.56s | 77 tps | 200K | $1.00 / $5.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.68% | 99.68% | 99.73% | 721ms | 3.97s | 82 tps | 200K | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/global | Healthy | 99.96% | 99.97% | 99.96% | 99.96% | 1.11s | 5.31s | 62 tps | 200K | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/us | No data | — | 99.93% | 99.77% | 99.84% | 957ms | 8.64s | 107 tps | 200K | $1.10 / $5.50 |
Googlegoogle-vertex/europe | No data | — | 100% | 100% | 99.99%◆ (best) | 521ms | 1.15s | 78 tps | 200K | $1.10 / $5.50 |
Googlegoogle-vertex/us-east5 | No data | — | 100% | 100%◆ (best) | 99.96% | 2.57s | 3.46s | 193 tps◆ (best) | 200K | $1.10 / $5.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.85%
- 7d
- 99.90%
- 30d
- 99.96%
- p50
- 514ms
- p99
- 1.04s◆ (best)
- Throughput
- 91 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/eu-west-1 - Anthropic100%◆ (best)Healthy24h 99.96%
- 7d
- 99.90%
- 30d
- 99.94%
- p50
- 375ms◆ (best)
- p99
- 1.64s
- Throughput
- 90 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
anthropic - Azure100%◆ (best)Healthy24h 99.90%
- 7d
- 99.77%
- 30d
- 99.89%
- p50
- 491ms
- p99
- 3.56s
- Throughput
- 77 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
azure/global - Google100%◆ (best)Healthy24h 99.68%
- 7d
- 99.68%
- 30d
- 99.73%
- p50
- 721ms
- p99
- 3.97s
- Throughput
- 82 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
google-vertex/global - Amazon Bedrock99.96%Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.96%
- p50
- 1.11s
- p99
- 5.31s
- Throughput
- 62 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
amazon-bedrock/global - No data24h 99.93%
- 7d
- 99.77%
- 30d
- 99.84%
- p50
- 957ms
- p99
- 8.64s
- Throughput
- 107 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/us - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%◆ (best)
- p50
- 521ms
- p99
- 1.15s
- Throughput
- 78 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
google-vertex/europe - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.96%
- p50
- 2.57s
- p99
- 3.46s
- Throughput
- 193 tps◆ (best)
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
google-vertex/us-east5
Measured 5m 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.