GPT-5.4: 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 | Healthy | 100%◆ (best) | 99.96% | 99.93% | 99.93% | 3.60s | 25.0s | 52 tps | 1.1M | $2.50 / $15.00 |
Azureazure/eu | Healthy | 100%◆ (best) | 100% | 100%◆ (best) | 100%◆ (best) | 2.80s | 9.80s | 56 tps | 1.1M | $2.75 / $16.50 |
OpenAIopenai | Healthy | 98.52% | 99.15% | 99.36% | 99.36% | 1.21s◆ (best) | 37.3s | 39 tps | 1.1M | $2.50 / $15.00 |
OpenAIopenai/flex | Healthy | 98.52% | 99.15% | 99.36% | 99.36% | 43.7s | 92.5s | 58 tps | 1.1M | $1.25 / $7.50◆ (best) |
OpenAIopenai/priority | Healthy | 98.52% | 99.15% | 99.36% | 99.36% | 1.94s | 5.97s◆ (best) | 77 tps◆ (best) | 1.1M | $5.00 / $30.00 |
Amazon Bedrockamazon-bedrock/us-east-1 | No data | — | — | — | — | — | — | — | 1.1M | $2.75 / $16.50 |
Azureazure/us | No data | — | 98.79% | 100%◆ (best) | 100%◆ (best) | — | — | — | 1.1M | $2.75 / $16.50 |
- Azure100%◆ (best)Healthy24h 99.96%
- 7d
- 99.93%
- 30d
- 99.93%
- p50
- 3.60s
- p99
- 25.0s
- Throughput
- 52 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
azure - Azure100%◆ (best)Healthy24h 100%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- 2.80s
- p99
- 9.80s
- Throughput
- 56 tps
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/eu - OpenAI98.52%Healthy24h 99.15%
- 7d
- 99.36%
- 30d
- 99.36%
- p50
- 1.21s◆ (best)
- p99
- 37.3s
- Throughput
- 39 tps
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai - OpenAI98.52%Healthy24h 99.15%
- 7d
- 99.36%
- 30d
- 99.36%
- p50
- 43.7s
- p99
- 92.5s
- Throughput
- 58 tps
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50◆ (best)
openai/flex - OpenAI98.52%Healthy24h 99.15%
- 7d
- 99.36%
- 30d
- 99.36%
- p50
- 1.94s
- p99
- 5.97s◆ (best)
- Throughput
- 77 tps◆ (best)
- 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 98.79%
- 7d
- 100%◆ (best)
- 30d
- 100%◆ (best)
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.75 / $16.50
azure/us
Measured 4m 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.
Throughput
Median tokens per second.