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/us | Healthy | 100%◆ (best) | 99.90% | 99.74% | 99.83% | 1.14s | 2.90s | 75 tps | 200K | $1.10 / $5.50 |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.93% | 99.90% | 99.94% | 616ms | 1.94s | 74 tps | 200K | $1.00 / $5.00◆ (best) |
Azureazure/global | Healthy | 100%◆ (best) | 99.99% | 99.74% | 99.89% | 434ms | 1.88s | 73 tps | 200K | $1.00 / $5.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.52% | 99.63% | 99.74% | 531ms | 3.86s | 85 tps | 200K | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/global | Healthy | 99.99% | 99.95% | 99.95% | 99.96% | 761ms | 4.55s | 69 tps | 200K | $1.00 / $5.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.97% | 99.92% | 99.96% | 602ms | 2.26s | 111 tps | 200K | $1.10 / $5.50 |
Googlegoogle-vertex/europe | No data | — | 100% | 100% | 99.99%◆ (best) | 400ms◆ (best) | 1.10s◆ (best) | 80 tps | 200K | $1.10 / $5.50 |
Googlegoogle-vertex/us-east5 | No data | — | 99.94% | 100%◆ (best) | 99.96% | 2.56s | 2.69s | 195 tps◆ (best) | 200K | $1.10 / $5.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.90%
- 7d
- 99.74%
- 30d
- 99.83%
- p50
- 1.14s
- p99
- 2.90s
- Throughput
- 75 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/us - Anthropic100%◆ (best)Healthy24h 99.93%
- 7d
- 99.90%
- 30d
- 99.94%
- p50
- 616ms
- p99
- 1.94s
- Throughput
- 74 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
anthropic - Azure100%◆ (best)Healthy24h 99.99%
- 7d
- 99.74%
- 30d
- 99.89%
- p50
- 434ms
- p99
- 1.88s
- Throughput
- 73 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
azure/global - Google100%◆ (best)Healthy24h 99.52%
- 7d
- 99.63%
- 30d
- 99.74%
- p50
- 531ms
- p99
- 3.86s
- Throughput
- 85 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
google-vertex/global - Amazon Bedrock99.99%Healthy24h 99.95%
- 7d
- 99.95%
- 30d
- 99.96%
- p50
- 761ms
- p99
- 4.55s
- Throughput
- 69 tps
- Context
- 200K
- $/Mtok
- $1.00 / $5.00◆ (best)
amazon-bedrock/global - No data24h 99.97%
- 7d
- 99.92%
- 30d
- 99.96%
- p50
- 602ms
- p99
- 2.26s
- Throughput
- 111 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%◆ (best)
- p50
- 400ms◆ (best)
- p99
- 1.10s◆ (best)
- Throughput
- 80 tps
- Context
- 200K
- $/Mtok
- $1.10 / $5.50
google-vertex/europe - No data24h 99.94%
- 7d
- 100%◆ (best)
- 30d
- 99.96%
- p50
- 2.56s
- p99
- 2.69s
- Throughput
- 195 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.
Throughput
Median tokens per second.