Claude Opus 4.6: 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) | 99.89% | 99.88% | 99.88% | 1.47s◆ (best) | 3.38s◆ (best) | 33 tps | 1.0M | $5.00 / $25.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.70% | 99.76% | 99.76% | 2.53s | 14.8s | 32 tps | 1.0M | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 99.92% | 99.89% | 99.86% | 99.86% | 1.75s | 5.20s | 35 tps◆ (best) | 1.0M | $5.00 / $25.00◆ (best) |
Azureazure/global | No data | — | 99.84% | — | — | 2.89s | 9.09s | 30 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/global | No data | — | 99.97% | 99.99% | 99.99% | 1.95s | 5.30s | 34 tps | 1.0M | $5.00 / $25.00◆ (best) |
- Amazon Bedrock100%◆ (best)Healthy24h 99.89%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 1.47s◆ (best)
- p99
- 3.38s◆ (best)
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - Anthropic100%◆ (best)Healthy24h 99.70%
- 7d
- 99.76%
- 30d
- 99.76%
- p50
- 2.53s
- p99
- 14.8s
- Throughput
- 32 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - Claude Platform on AWS99.92%Healthy24h 99.89%
- 7d
- 99.86%
- 30d
- 99.86%
- p50
- 1.75s
- p99
- 5.20s
- Throughput
- 35 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - No data24h 99.84%
- 7d
- —
- 30d
- —
- p50
- 2.89s
- p99
- 9.09s
- Throughput
- 30 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/global - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/europe - No data24h 99.97%
- 7d
- 99.99%
- 30d
- 99.99%
- p50
- 1.95s
- p99
- 5.30s
- Throughput
- 34 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global
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.