Claude Opus 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) | 99.88% | 99.85% | 99.85% | 4.40s | 19.5s | 62 tps | 1.0M | $4.00 / $20.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.98% | 100%◆ (best) | 100%◆ (best) | 4.45s | 15.8s | 73 tps | 1.0M | $4.00 / $20.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.99% | 100% | 100% | 4.46s | 15.8s | 55 tps | 1.0M | $4.00 / $20.00◆ (best) |
Googlegoogle-vertex/europe | Healthy | 100%◆ (best) | 100% | — | — | 1.79s◆ (best) | 4.02s◆ (best) | 26 tps | 1.0M | $4.40 / $22.00 |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.94% | 99.83% | 99.83% | 3.17s | 11.6s | 71 tps | 1.0M | $4.00 / $20.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | — | — | 3.67s | 9.30s | 79 tps | 1.0M | $4.40 / $22.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | — | — | 3.55s | 4.57s | 63 tps | 1.0M | $4.40 / $22.00 |
Anthropicanthropic/fast | No data | — | 100% | — | — | 3.39s | 10.4s | 73 tps | 1.0M | $8.00 / $40.00 |
Azureazure/global | No data | — | 99.98% | — | — | 3.79s | 5.03s | 97 tps◆ (best) | 1.0M | $4.00 / $20.00◆ (best) |
Azureazure/us | No data | — | — | — | — | — | — | — | 1.0M | $4.40 / $22.00 |
Googlegoogle-vertex/us | No data | — | 100% | — | — | 2.76s | 4.25s | 74 tps | 1.0M | $4.40 / $22.00 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.88%
- 7d
- 99.85%
- 30d
- 99.85%
- p50
- 4.40s
- p99
- 19.5s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00◆ (best)
amazon-bedrock - Anthropic100%◆ (best)Healthy24h 99.98%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 4.45s
- p99
- 15.8s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00◆ (best)
anthropic - Claude Platform on AWS100%◆ (best)Healthy24h 99.99%
- 7d
- 100%
- 30d
- 100%
- p50
- 4.46s
- p99
- 15.8s
- Throughput
- 55 tps
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00◆ (best)
claude-on-aws - Google100%◆ (best)Healthy24h 100%
- 7d
- —
- 30d
- —
- p50
- 1.79s◆ (best)
- p99
- 4.02s◆ (best)
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $4.40 / $22.00
google-vertex/europe - Google100%◆ (best)Healthy24h 99.94%
- 7d
- 99.83%
- 30d
- 99.83%
- p50
- 3.17s
- p99
- 11.6s
- Throughput
- 71 tps
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00◆ (best)
google-vertex/global - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 3.67s
- p99
- 9.30s
- Throughput
- 79 tps
- Context
- 1.0M
- $/Mtok
- $4.40 / $22.00
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 3.55s
- p99
- 4.57s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $4.40 / $22.00
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 3.39s
- p99
- 10.4s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $8.00 / $40.00
anthropic/fast - No data24h 99.98%
- 7d
- —
- 30d
- —
- p50
- 3.79s
- p99
- 5.03s
- Throughput
- 97 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $4.00 / $20.00◆ (best)
azure/global - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $4.40 / $22.00
azure/us - No data24h 100%
- 7d
- —
- 30d
- —
- p50
- 2.76s
- p99
- 4.25s
- Throughput
- 74 tps
- Context
- 1.0M
- $/Mtok
- $4.40 / $22.00
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, averaged over the hour.
Throughput
Median tokens per second.