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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Anthropicanthropic | Healthy | 100%◆ (best) | 99.97% | 99.88% | 99.88% | 1.05s | 7.30s | 57 tps | 1.0M | $5.00 / $25.00◆ (best) |
Claude Platform on AWSclaude-on-aws | Healthy | 100%◆ (best) | 99.99% | 99.68% | 99.91% | 1.08s | 6.79s | 67 tps | 1.0M | $5.00 / $25.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 100%◆ (best) | 99.97% | 99.96% | 99.97% | 2.54s | 29.3s | 82 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock | No data | — | 92.49% | 99.69% | 99.80% | 2.70s | 65.6s | 72 tps | 1.0M | $5.00 / $25.00◆ (best) |
Amazon Bedrockamazon-bedrock/eu-west-1 | No data | — | 100% | 100%◆ (best) | 99.99% | 1.25s | 2.13s | 57 tps | 1.0M | $5.50 / $27.50 |
Amazon Bedrockamazon-bedrock/us | No data | — | 100% | 99.92% | 99.94% | 746ms◆ (best) | 893ms◆ (best) | 77 tps | 1.0M | $5.50 / $27.50 |
Anthropicanthropic/fast | No data | — | 100% | 100% | 99.98% | 1.34s | 3.30s | 141 tps◆ (best) | 1.0M | $10.00 / $50.00 |
Azureazure/global | No data | — | 95.87% | 100% | 99.99% | — | — | — | 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% | 100%◆ (best) | 100%◆ (best) | 1.06s | 1.34s | 100 tps | 1.0M | $5.50 / $27.50 |
Googlegoogle-vertex/us | No data | — | — | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.0M | $5.50 / $27.50 |
- Anthropic100%◆ (best)Healthy24h 99.97%
- 7d
- 99.88%
- 30d
- 99.88%
- p50
- 1.05s
- p99
- 7.30s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
anthropic - Claude Platform on AWS100%◆ (best)Healthy24h 99.99%
- 7d
- 99.68%
- 30d
- 99.91%
- p50
- 1.08s
- p99
- 6.79s
- Throughput
- 67 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
claude-on-aws - Google100%◆ (best)Healthy24h 99.97%
- 7d
- 99.96%
- 30d
- 99.97%
- p50
- 2.54s
- p99
- 29.3s
- Throughput
- 82 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
google-vertex/global - No data24h 92.49%
- 7d
- 99.69%
- 30d
- 99.80%
- p50
- 2.70s
- p99
- 65.6s
- Throughput
- 72 tps
- Context
- 1.0M
- $/Mtok
- $5.00 / $25.00◆ (best)
amazon-bedrock - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 99.99%
- p50
- 1.25s
- p99
- 2.13s
- Throughput
- 57 tps
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/eu-west-1 - No data24h 100%
- 7d
- 99.92%
- 30d
- 99.94%
- p50
- 746ms◆ (best)
- p99
- 893ms◆ (best)
- Throughput
- 77 tps
- Context
- 1.0M
- $/Mtok
- $5.50 / $27.50
amazon-bedrock/us - No data24h 100%
- 7d
- 100%
- 30d
- 99.98%
- p50
- 1.34s
- p99
- 3.30s
- Throughput
- 141 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00
anthropic/fast - No data24h 95.87%
- 7d
- 100%
- 30d
- 99.99%
- p50
- —
- p99
- —
- Throughput
- —
- 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 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.06s
- p99
- 1.34s
- Throughput
- 100 tps
- 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 3m 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.