Claude Opus 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) | 99.94% | 99.98% | 99.93% | 3.07s | 20.5s | 62 tps | 1.0M | $5.00 / $25.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.83% | 99.94% | 99.93% | 2.31s | 9.28s | 68 tps | 1.0M | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.98% | 99.89% | 99.88% | 4.09s | 23.2s | 63 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 99.69% | 99.98% | 99.97% | 4.13s | 4.74s | 78 tps | 1.0M | $5.50 / $27.50 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | 100% | 100%◆ (best) | 100% | — | — | — | 1.0M | $5.50 / $27.50 |
Anthropicanthropic/fast | No data | — | 100% | 100%◆ (best) | 100% | 1.28s◆ (best) | 2.78s◆ (best) | 137 tps◆ (best) | 1.0M | $10.00 / $50.00 |
Azureazure/global | No data | — | 100% | 100% | 99.99% | 5.31s | 5.65s | 80 tps | 1.0M | $5.00 / $25.00◆ (best) |
Azureazure/us | No data | — | — | 100%◆ (best) | 99.95% | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/europe | No data | — | 100% | 99.99% | 99.98% | 1.89s | 4.80s | 73 tps | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/global | No data | — | 99.98% | 99.99% | 99.94% | 2.32s | 6.94s | 60 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/us | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.94%
- 7d
- 99.98%
- 30d
- 99.93%
- p50
- 3.07s
- p99
- 20.5s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - Anthropic100%◆ (best)Healthy24h 99.83%
- 7d
- 99.94%
- 30d
- 99.93%
- p50
- 2.31s
- p99
- 9.28s
- Throughput
- 68 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - Claude Platform on AWS100%◆ (best)Healthy24h 99.98%
- 7d
- 99.89%
- 30d
- 99.88%
- p50
- 4.09s
- p99
- 23.2s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - No data24h 99.69%
- 7d
- 99.98%
- 30d
- 99.97%
- p50
- 4.13s
- p99
- 4.74s
- Throughput
- 78 tps
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%
- p50
- 1.28s◆ (best)
- p99
- 2.78s◆ (best)
- Throughput
- 137 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00
anthropic/fast - No data24h 100%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 5.31s
- p99
- 5.65s
- Throughput
- 80 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/global - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.95%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
azure/us - No data24h 100%
- 7d
- 99.99%
- 30d
- 99.98%
- p50
- 1.89s
- p99
- 4.80s
- Throughput
- 73 tps
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/europe - No data24h 99.98%
- 7d
- 99.99%
- 30d
- 99.94%
- p50
- 2.32s
- p99
- 6.94s
- Throughput
- 60 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
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.