GPT-5.4
openai/gpt-5.4
Compare with GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.4 Pro
CompareGPT-5.4
| State | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.97% | 99.93% | 99.93% | 3.97s | 33.3s | 45 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai | Healthy | 99.73% | 99.44% | 99.42% | 99.42% | 1.07s | 10.2s | 46 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 99.73% | 99.44% | 99.42% | 99.42% | 35.0s | 115s | 45 tps | 1.1M | $1.25 / $7.50 |
OpenAIopenai/priority | Healthy | 99.73% | 99.44% | 99.42% | 99.42% | 2.73s | 14.3s | 108 tps | 1.1M | $5.00 / $30.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | — | — | — | — | — | 1.1M | $2.75 / $16.50 |
Azureazure/eu | No data | — | 100% | 100% | 100% | 1.79s | 2.38s | 79 tps | 1.1M | $2.75 / $16.50 |
Azureazure/us | No data | — | 98.79% | 100% | 100% | — | — | — | 1.1M | $2.75 / $16.50 |
- Azure100%Healthy24h 99.97%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 3.97s
- p99
- 33.3s
- Throughput
- 45 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
azure - OpenAI99.73%Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 1.07s
- p99
- 10.2s
- Throughput
- 46 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI99.73%Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 35.0s
- p99
- 115s
- Throughput
- 45 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50
openai/flex - OpenAI99.73%Healthy24h 99.44%
- 7d
- 99.42%
- 30d
- 99.42%
- p50
- 2.73s
- p99
- 14.3s
- Throughput
- 108 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai/priority - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
amazon-bedrock/us-east-1 - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 1.79s
- p99
- 2.38s
- Throughput
- 79 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/eu - No data24h 98.79%
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/us
Measured 3m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
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.