May 28th update to the original DeepSeek R1 Performance on par with OpenAI o1, but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...
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 |
|---|---|---|---|---|---|---|---|
| 164K | $0.50 | $2.15 | $0.35 | — | — | 100.00% | |
| 164K | $0.50 | $2.18 | — | — | — | 100.00% | |
| 128K | $0.571 | $2.29 | — | — | — | 100.00% | |
| 164K | $0.70 | $2.50 | $0.35 | — | — | 100.00% |