GPT-4 Turbo vs GPT-4o
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 TurboGPT-4o
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| GPT-4 Turbo | 0/1 | — | — | — | — | 128K | $10.00 / $30.00 OpenAI |
| GPT-4o | 2/2 | 100% Azure | 663ms OpenAI | 5.40s OpenAI | 48 tps Azure | 128K | $2.50 / $10.00 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.