GPT-5 Nano
openai/gpt-5-nanoInputOutput
Compare its 4 providersIncident RSSCompare with GPT-5.4 Nano, GPT-5 Nano (batch), GPT-4.1 Nano
CompareGPT-5 Nano
- Azure100%Healthy24h 100%
- 7d
- 99.97%
- 30d
- 99.98%
- p50
- 960ms
- p99
- 12.7s
- Throughput
- 83 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
azure - OpenAI100%Healthy24h 99.99%
- 7d
- 99.91%
- 30d
- 98.91%
- p50
- 2.26s
- p99
- 13.9s
- Throughput
- 120 tps
- Context
- 400K
- $/Mtok
- $0.050 / $0.400
openai - OpenAI100%Healthy24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- 1.01s
- p99
- 3.40s
- Throughput
- 135 tps
- Context
- 400K
- $/Mtok
- $0.025 / $0.200
openai/flex - No data24h 100%
- 7d
- 100%
- 30d
- 100%
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 400K
- $/Mtok
- $0.055 / $0.440
azure/swedencentral
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
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.
Daily availability
One row per endpoint · one dot per day · last 90 days.
worst hour ≥ 95%90–95%< 90%no data
Colour by each endpoint's worst hour of each UTC day · 4 endpoints · 47 days with data, 1 endpoint-day below 90%.