1models tracked · ranked by intelligence, speed & price
its fastest is Cogito v2.1 671B at 28 tokens/sec, and its cheapest is Cogito v2.1 671B at $1.25 per million input tokens. All 1 Deep Cogito models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| cogito-v2.1-671b ReasoningJSON | — | 28 | 339ms | $1.25 | 128K |