Claude Fable 5: 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 | 99.35% | 99.81% | 99.83% | 99.82% | 3.56s | 13.0s | 56 tps | 1.0M | $10.00 / $50.00◆ (best) |
Amazon Bedrockamazon-bedrock | No data | — | — | — | — | 4.34s | 7.74s | 33 tps | 1.0M | $10.00 / $50.00◆ (best) |
Azureazure | No data | — | 99.87% | 94.81% | 96.93% | 3.52s◆ (best) | 5.55s | 52 tps | 1.0M | $10.00 / $50.00◆ (best) |
Claude Platform on AWSclaude-on-aws | No data | — | 100% | 84.32% | 98.51% | 3.61s | 4.41s◆ (best) | 13 tps | 1.0M | $10.00 / $50.00◆ (best) |
Googlegoogle-vertex/europe | No data | — | 99.68% | 99.30% | 99.80% | — | — | — | 1.0M | $11.00 / $55.00 |
Googlegoogle-vertex/global | No data | — | 99.91% | 100%◆ (best) | 100%◆ (best) | 3.85s | 4.68s | 60 tps◆ (best) | 1.0M | $10.00 / $50.00◆ (best) |
- Anthropic99.35%Healthy24h 99.81%
- 7d
- 99.83%
- 30d
- 99.82%
- p50
- 3.56s
- p99
- 13.0s
- Throughput
- 56 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
anthropic - No data24h —
- 7d
- —
- 30d
- —
- p50
- 4.34s
- p99
- 7.74s
- Throughput
- 33 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
amazon-bedrock - No data24h 99.87%
- 7d
- 94.81%
- 30d
- 96.93%
- p50
- 3.52s◆ (best)
- p99
- 5.55s
- Throughput
- 52 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
azure - No data24h 100%
- 7d
- 84.32%
- 30d
- 98.51%
- p50
- 3.61s
- p99
- 4.41s◆ (best)
- Throughput
- 13 tps
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
claude-on-aws - No data24h 99.68%
- 7d
- 99.30%
- 30d
- 99.80%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.0M
- $/Mtok
- $11.00 / $55.00
google-vertex/europe - No data24h 99.91%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 3.85s
- p99
- 4.68s
- Throughput
- 60 tps◆ (best)
- Context
- 1.0M
- $/Mtok
- $10.00 / $50.00◆ (best)
google-vertex/global
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.