Claude Opus 4.7: 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) | 99.98% | 99.98% | 99.80% | 775ms | 7.66s | 72 tps | 1.0M | $5.00 / $25.00◆ (best) |
Anthropicanthropic | Healthy | 100%◆ (best) | 99.95% | 99.99% | 99.97% | 705ms◆ (best) | 4.20s | 37 tps | 1.0M | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.99% | 99.60% | 99.90% | 2.07s | 15.4s | 28 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Azureazure/global | No data | — | — | 100%◆ (best) | 100%◆ (best) | 1.12s | 1.12s◆ (best) | 36 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/global | No data | — | 99.95% | 100%◆ (best) | 99.99% | 1.04s | 6.77s | 75 tps◆ (best) | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/us | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
- Amazon Bedrock100%◆ (best)Healthy24h 99.98%
- 7d
- 99.98%
- 30d
- 99.80%
- p50
- 775ms
- p99
- 7.66s
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock/global - Anthropic100%◆ (best)Healthy24h 99.95%
- 7d
- 99.99%
- 30d
- 99.97%
- p50
- 705ms◆ (best)
- p99
- 4.20s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - Claude Platform on AWS100%◆ (best)Healthy24h 99.99%
- 7d
- 99.60%
- 30d
- 99.90%
- p50
- 2.07s
- p99
- 15.4s
- Throughput
- 28 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/eu-west-1 - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.12s
- p99
- 1.12s◆ (best)
- Throughput
- 36 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
azure/global - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/europe - No data24h 99.95%
- 7d
- 100%◆ (best)
- 30d
- 99.99%
- p50
- 1.04s
- p99
- 6.77s
- Throughput
- 75 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/us
Measured 2m 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.