GPT-4.1 Nano (batch) vs GPT-4.1
One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.
CompareGPT-4.1 Nano (batch)GPT-4.1
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| GPT-4.1 Nano (batch) | 0/1 | — | — | — | — | 1.0M | $0.050 / $0.200 OpenAI |
| GPT-4.1 | 2/3 | 100% Azure | 656ms OpenAI | 4.10s Azure | 40 tps OpenAI | 1.0M | $2.00 / $8.00 Azure |
History
Availability
Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.
Time to first token
Fastest p50 available from any provider. Logarithmic axis.
Throughput
Best median tokens per second available.