GPT-5.4
openai/gpt-5.4
Compare with GPT-5.4 Mini, GPT-5.4 Nano, GPT-5.4 Pro
CompareGPT-5.4
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.97% | 2.56s | 29.0s | 51 tps | 1.1M | $2.50 / $15.00 |
Azureazure/eu | Healthy | 100% | 100% | 3.30s | 9.89s | 51 tps | 1.1M | $2.75 / $16.50 |
OpenAIopenai | Healthy | 99.53% | 99.68% | 994ms | 8.58s | 32 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 99.53% | 99.68% | 15.6s | 28.4s | 7.0 tps | 1.1M | $1.25 / $7.50 |
OpenAIopenai/priority | Healthy | 99.53% | 99.68% | 1.89s | 8.32s | 74 tps | 1.1M | $5.00 / $30.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | — | — | — | 1.1M | $2.75 / $16.50 |
Azureazure/us | No data | — | 100% | 8.35s | 8.35s | 34 tps | 1.1M | $2.75 / $16.50 |
- Azure100%Healthy24h 99.97%
- p50
- 2.56s
- p99
- 29.0s
- Throughput
- 51 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
azure - Azure100%Healthy24h 100%
- p50
- 3.30s
- p99
- 9.89s
- Throughput
- 51 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/eu - OpenAI99.53%Healthy24h 99.68%
- p50
- 994ms
- p99
- 8.58s
- Throughput
- 32 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI99.53%Healthy24h 99.68%
- p50
- 15.6s
- p99
- 28.4s
- Throughput
- 7.0 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50
openai/flex - OpenAI99.53%Healthy24h 99.68%
- p50
- 1.89s
- p99
- 8.32s
- Throughput
- 74 tps
- Context
- 1.1M
- $/Mtok
- $5.00 / $30.00
openai/priority - Amazon Bedrock—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
amazon-bedrock/us-east-1 - Azure—No data24h 100%
- p50
- 8.35s
- p99
- 8.35s
- Throughput
- 34 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/us
Measured 55s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
2 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.