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/global | Healthy | 100%◆ (best) | 99.96% | 99.95% | 99.96% | 768ms | 4.21s | 68 tps | 200K | $1.00 / $5.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.94% | 99.90% | 99.94% | 573ms | 2.48s | 71 tps | 200K | $1.00 / $5.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.47% | 99.63% | 99.74% | 810ms | 3.99s | 85 tps | 200K | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.95% | 99.92% | 99.96% | 567ms | 567ms◆ (best) | 79 tps | 200K | $1.10 / $5.50 |
Amazon Bedrockamazon-bedrock/us | No data | — | 99.90% | 99.74% | 99.83% | 498ms◆ (best) | 861ms | 78 tps | 200K | $1.10 / $5.50 |
Azureazure/global | No data | — | 99.99% | 99.74% | 99.89% | 659ms | 1.94s | 83 tps | 200K | $1.00 / $5.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | 100% | 100% | 99.99%◆ (best) | 871ms | 1.72s | 72 tps | 200K | $1.10 / $5.50 |
Googlegoogle-vertex/us-east5 | No data | — | 99.94% | 100%◆ (best) | 99.96% | 1.67s | 3.28s | 192 tps◆ (best) | 200K | $1.10 / $5.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.96%
- 7d
- 99.95%
- 30d
- 99.96%
- p50
- 768ms
- p99
- 4.21s
- Throughput
- 68 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
amazon-bedrock/global - Anthropic100%◆ (best)Healthy24h 99.94%
- 7d
- 99.90%
- 30d
- 99.94%
- p50
- 573ms
- p99
- 2.48s
- Throughput
- 71 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
anthropic - Google100%◆ (best)Healthy24h 99.47%
- 7d
- 99.63%
- 30d
- 99.74%
- p50
- 810ms
- p99
- 3.99s
- Throughput
- 85 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
google-vertex/global - No data24h 99.95%
- 7d
- 99.92%
- 30d
- 99.96%
- p50
- 567ms
- p99
- 567ms◆ (best)
- Throughput
- 79 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/eu-west-1 - No data24h 99.90%
- 7d
- 99.74%
- 30d
- 99.83%
- p50
- 498ms◆ (best)
- p99
- 861ms
- Throughput
- 78 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/us - No data24h 99.99%
- 7d
- 99.74%
- 30d
- 99.89%
- p50
- 659ms
- p99
- 1.94s
- Throughput
- 83 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
azure/global - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%◆ (best)
- p50
- 871ms
- p99
- 1.72s
- Throughput
- 72 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
google-vertex/europe - No data24h 99.94%
- 7d
- 100%◆ (best)
- 30d
- 99.96%
- p50
- 1.67s
- p99
- 3.28s
- Throughput
- 192 tps◆ (best)
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
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, averaged over the hour.
Throughput
Median tokens per second.