4models tracked · ranked by intelligence, speed & price
its fastest is Command R7B (12-2024) at 57 tokens/sec, and its cheapest is Command R7B (12-2024) at $0.037 per million input tokens. All 4 Cohere models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| command-a JSON | — | 54 | 242ms | $2.50 | 256K |
| command-r7b-12-2024 JSON | — | 57 | 226ms | $0.037 | 128K |
| command-r-plus-08-2024 ToolsJSON | — | 39 | 421ms | $2.50 | 128K |
| command-r-08-2024 ToolsJSON | — | 55 | 223ms | $0.150 | 128K |