1models tracked · ranked by intelligence, speed & price
its cheapest is Jamba Large 1.7 at $2.00 per million input tokens. All 1 AI21 models are compared below by intelligence, speed, latency, context and price.
| Model | Intel | Speed | Latency | In $/M | Context |
|---|---|---|---|---|---|
| jamba-large-1.7 ToolsJSON | — | — | — | $2.00 | 256K |