gpt-oss-20b (batch) 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-oss-20b (batch)GPT Audio
| gpt-oss-20b (batch) | 0/1 | — | — | — | — | — | — | 131K | $0.050 / $0.200 |
| GPT Audio | 0/1 | — | — | — | — | — | — | 128K | $2.50 / $10.00 |
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.