GPT-3.5 Turbo Instruct vs GPT Audio
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-3.5 Turbo InstructGPT Audio
| Model | Providers | Best uptime | Fastest p50 | Best p99 | Throughput | Context | Cheapest $/Mtok |
|---|---|---|---|---|---|---|---|
| GPT-3.5 Turbo Instruct | 0/1 | — | — | — | — | 4K | $1.50 / $2.00 OpenAI |
| GPT Audio | 0/1 | — | — | — | — | 128K | $2.50 / $10.00 OpenAI |
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.