Claude Opus 4.8: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Claude Platform on AWSclaude-on-aws | Healthy | 99.87%◆ (best) | 99.99% | 99.68% | 99.90% | 1.49s | 21.6s | 63 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 99.51% | 99.97% | 99.96% | 99.97% | 1.10s | 30.4s | 81 tps | 1.0M | $5.00 / $25.00◆ (best) |
Anthropicanthropic | Healthy | 98.55% | 99.98% | 99.88% | 99.86% | 996ms | 4.85s | 52 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock | No data | — | 95.89% | 99.92% | 99.84% | 3.58s | 49.6s | 61 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 99.99% | — | — | — | 1.0M | $5.50 / $27.50 |
Amazon Bedrockamazon-bedrock/us | No data | — | 100% | 99.90% | 99.94% | — | — | — | 1.0M | $5.50 / $27.50 |
Anthropicanthropic/fast | No data | — | 100% | 100% | 99.98% | 898ms◆ (best) | 3.74s◆ (best) | 174 tps◆ (best) | 1.0M | $10.00 / $50.00 |
Azureazure/global | No data | — | 98.01% | 100% | 99.99% | 22.7s | 22.7s | 71 tps | 1.0M | $5.00 / $25.00◆ (best) |
Azureazure/us | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/europe | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/us | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
- Claude Platform on AWS99.87%◆ (best)Healthy24h 99.99%
- 7d
- 99.68%
- 30d
- 99.90%
- p50
- 1.49s
- p99
- 21.6s
- Throughput
- 63 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - Google99.51%Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.97%
- p50
- 1.10s
- p99
- 30.4s
- Throughput
- 81 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - Anthropic98.55%Healthy24h 99.98%
- 7d
- 99.88%
- 30d
- 99.86%
- p50
- 996ms
- p99
- 4.85s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - No data24h 95.89%
- 7d
- 99.92%
- 30d
- 99.84%
- p50
- 3.58s
- p99
- 49.6s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.99%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- 99.90%
- 30d
- 99.94%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/us - No data24h 100%
- 7d
- 100%
- 30d
- 99.98%
- p50
- 898ms◆ (best)
- p99
- 3.74s◆ (best)
- Throughput
- 174 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00
anthropic/fast - No data24h 98.01%
- 7d
- 100%
- 30d
- 99.99%
- p50
- 22.7s
- p99
- 22.7s
- Throughput
- 71 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
azure/us - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/europe - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
google-vertex/us
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.