GPT-5.5: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
OpenAIopenai | Healthy | 100% | 100% | 99.92% | 99.58% | 2.19s | 17.3s | 59 tps | 1.1M | $5.00 / $30.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | 98.55% | 99.64% | 1.29s◆ (best) | 7.74s | 72 tps | 1.1M | $5.50 / $33.00 |
Azureazure | No data | — | 99.99% | 99.97% | 99.92% | 6.21s | 23.6s | 47 tps | 1.1M | $5.00 / $30.00 |
Azureazure/eu | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 2.56s | 5.28s | 89 tps | 1.1M | $5.50 / $33.00 |
Azureazure/us | No data | — | — | 100%◆ (best) | 99.80% | 4.06s | 6.15s | 84 tps | 1.1M | $5.50 / $33.00 |
OpenAIopenai/fast | No data | — | 100% | 100%◆ (best) | 100%◆ (best) | 1.67s | 1.95s◆ (best) | 116 tps◆ (best) | 1.1M | $12.50 / $75.00 |
OpenAIopenai/flex | No data | — | 100% | 100%◆ (best) | 100% | — | — | — | 1.1M | $2.50 / $15.00◆ (best) |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 1.1M | $12.50 / $75.00 |
- OpenAI100%Healthy24h 100%
- 7d
- 99.92%
- 30d
- 99.58%
- p50
- 2.19s
- p99
- 17.3s
- Throughput
- 59 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai - No data24h —
- 7d
- 98.55%
- 30d
- 99.64%
- p50
- 1.29s◆ (best)
- p99
- 7.74s
- Throughput
- 72 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
amazon-bedrock/us-east-1 - No data24h 99.99%
- 7d
- 99.97%
- 30d
- 99.92%
- p50
- 6.21s
- p99
- 23.6s
- Throughput
- 47 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
azure - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.56s
- p99
- 5.28s
- Throughput
- 89 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/eu - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.80%
- p50
- 4.06s
- p99
- 6.15s
- Throughput
- 84 tps
- Context
- 1.1M
- $/Mtok
- $5.50 / $33.00
azure/us - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 1.67s
- p99
- 1.95s◆ (best)
- Throughput
- 116 tps◆ (best)
- Context
- 1.1M
- $/Mtok
- $12.50 / $75.00
openai/fast - No data24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $12.50 / $75.00
openai/priority
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, averaged over the hour.
Throughput
Median tokens per second.