GPT-4o mini is OpenAI's newest model after GPT-4 Omni, supporting both text and image inputs with text outputs. As their most advanced small model, it is many multiples more affordable...
Different carriers host the same model. Reroute routes each request to the best one on price and uptime, and fails over to the next if a carrier goes down.
| Provider | Context | Input /M | Output /M | Cache read /M | Latency | Throughput | Uptime |
|---|---|---|---|---|---|---|---|
| 128K | $0.15 | $0.60 | $0.075 | — | — | 100.00% | |
| 128K | $0.15 | $0.60 | $0.075 | — | — | 100.00% | |
| 128K | $0.165 | $0.66 | $0.0825 | — | — | — |