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% | 4.87s | 40.4s | 48 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai | Healthy | 99.60% | 99.49% | 1.23s | 11.0s | 40 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 99.60% | 99.49% | 590ms | 3.21s | 58 tps | 1.1M | $1.25 / $7.50 |
OpenAIopenai/priority | Healthy | 99.60% | 99.49% | 1.64s | 3.01s | 77 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% | 2.21s | 26.0s | 43 tps | 1.1M | $2.75 / $16.50 |
Azureazure/us | No data | — | 100% | 3.78s | 7.63s | 42 tps | 1.1M | $2.75 / $16.50 |
- Azure100%Healthy24h 99.97%
- p50
- 4.87s
- p99
- 40.4s
- Throughput
- 48 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
azure - OpenAI99.60%Healthy24h 99.49%
- p50
- 1.23s
- p99
- 11.0s
- Throughput
- 40 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI99.60%Healthy24h 99.49%
- p50
- 590ms
- p99
- 3.21s
- Throughput
- 58 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50
openai/flex - OpenAI99.60%Healthy24h 99.49%
- p50
- 1.64s
- p99
- 3.01s
- Throughput
- 77 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
- 2.21s
- p99
- 26.0s
- Throughput
- 43 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/eu - Azure—No data24h 100%
- p50
- 3.78s
- p99
- 7.63s
- Throughput
- 42 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/us
Measured 1m 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 and p99 are OpenRouter's rolling 30-minute windows.
Throughput
Median tokens per second.