GPT-5.4 (batch)
openai/gpt-5.4:batch
Compare with GPT-5.4, GPT-5.4 Mini, GPT-5.4 Nano
CompareGPT-5.4 (batch)
| Provider | State | Uptime 5m | 24h | p50 latency | p99 | Throughput | Context | $/Mtok |
|---|---|---|---|---|---|---|---|---|
OpenAIopenai | No data | — | — | — | — | — | 1.1M | $1.25 / $7.50 |
OpenAIopenai/flex | No data | — | — | — | — | — | 1.1M | $0.625 / $3.75 |
OpenAIopenai/priority | No data | — | — | — | — | — | 1.1M | $2.50 / $15.00 |
- OpenAI—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $1.25 / $7.50
openai - OpenAI—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $0.625 / $3.75
openai/flex - OpenAI—No data24h —
- p50
- —
- p99
- —
- Throughput
- —
- Context
- 1.1M
- $/Mtok
- $2.50 / $15.00
openai/priority
Measured 1m ago. Latency and throughput are OpenRouter's rolling 30-minute windows.
History
3 endpoints reporting no data are omitted from the charts.
No endpoints with data to chart.