GPT-4.1
openai/gpt-4.1
Compare with GPT-4.1 Mini, GPT-4.1 Nano, GPT Audio
CompareGPT-4.1
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
Azureazure | Healthy | 100% | 99.99% | 924ms | 4.08s | 26 tps | 1.0M | $2.00 / $8.00 |
OpenAIopenai | Healthy | 99.95% | 99.95% | 642ms | 4.36s | 37 tps | 1.0M | $2.00 / $8.00 |
Azureazure/swedencentral | No data | — | 100% | 887ms | 7.44s | 62 tps | 1.0M | $2.20 / $8.80 |
- Azure100%Healthy24h 99.99%
- p50
- 924ms
- p99
- 4.08s
- Throughput
- 26 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $8.00
azure - OpenAI99.95%Healthy24h 99.95%
- p50
- 642ms
- p99
- 4.36s
- Throughput
- 37 tps
- Context
- 1.0M
- $/Mtok
- $2.00 / $8.00
openai - Azure—No data24h 100%
- p50
- 887ms
- p99
- 7.44s
- Throughput
- 62 tps
- Context
- 1.0M
- $/Mtok
- $2.20 / $8.80
azure/swedencentral
Measured 47s ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
1 endpoint reporting no data is 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, averaged over the hour.
Throughput
Median tokens per second.