Claude Fable 5.1: 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 | 99.74%◆ (best) | 99.79% | 99.65% | 99.75%◆ (best) | 5.57s | 18.4s◆ (best) | 47 tps | 1.0M | $10.00 / $50.00◆ (best) |
Googlegoogle-vertex/global | Healthy | 98.20% | 99.68% | 99.68%◆ (best) | 99.62% | 4.69s | 28.2s | 61 tps | 1.0M | $10.00 / $50.00◆ (best) |
Amazon Bedrockamazon-bedrock | No data | — | — | — | — | 6.14s | 18.7s | 71 tps◆ (best) | 1.0M | $10.00 / $50.00◆ (best) |
Azureazure | No data | — | 99.96% | 99.67% | 99.69% | 3.82s◆ (best) | 19.6s | 2.0 tps | 1.0M | $10.00 / $50.00◆ (best) |
- Anthropic99.74%◆ (best)Healthy24h 99.79%
- 7d
- 99.65%
- 30d
- 99.75%◆ (best)
- p50
- 5.57s
- p99
- 18.4s◆ (best)
- Throughput
- 47 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
anthropic - Google98.20%Healthy24h 99.68%
- 7d
- 99.68%◆ (best)
- 30d
- 99.62%
- p50
- 4.69s
- p99
- 28.2s
- Throughput
- 61 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
google-vertex/global - No data24h —
- 7d
- —
- 30d
- —
- p50
- 6.14s
- p99
- 18.7s
- Throughput
- 71 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
amazon-bedrock - No data24h 99.96%
- 7d
- 99.67%
- 30d
- 99.69%
- p50
- 3.82s◆ (best)
- p99
- 19.6s
- Throughput
- 2.0 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
azure
Measured 53s 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.