GPT-5.4 Mini: 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 | ||||||||||
|---|---|---|---|---|---|---|---|---|---|---|
Azureazure | No data | — | — | 99.98% | 99.98% | — | — | — | 400K | $0.750 / $4.50 |
Azureazure/us | No data | — | — | 100%◆ (best) | 99.01% | — | — | — | 400K | $0.825 / $4.95 |
OpenAIopenai | No data | — | — | 99.92% | 99.63% | — | — | — | 400K | $0.750 / $4.50 |
OpenAIopenai/fast | No data | — | — | 99.98% | 99.98%◆ (best) | — | — | — | 400K | $1.50 / $9.00 |
OpenAIopenai/flex | No data | — | — | 100% | 99.00% | — | — | — | 400K | $0.375 / $2.25◆ (best) |
OpenAIopenai/priority | No data | — | — | — | — | — | — | — | 400K | $1.50 / $9.00 |
- No data24h —
- 7d
- 99.98%
- 30d
- 99.98%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.750 / $4.50
azure - No data24h —
- 7d
- 100%◆ (best)
- 30d
- 99.01%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.825 / $4.95
azure/us - No data24h —
- 7d
- 99.92%
- 30d
- 99.63%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.750 / $4.50
openai - No data24h —
- 7d
- 99.98%
- 30d
- 99.98%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $1.50 / $9.00
openai/fast - No data24h —
- 7d
- 100%
- 30d
- 99.00%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.375 / $2.25◆ (best)
openai/flex - No data24h —
- 7d
- —
- 30d
- —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $1.50 / $9.00
openai/priority
No recent measurement. ◆ marks the best value in each column among these endpoints.
Price vs latency
No endpoint currently reports both a price and a latency.
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.