Jamba Large 1.7 is the latest model in the Jamba open family, offering improvements in grounding, instruction-following, and overall efficiency. Built on a hybrid SSM-Transformer architecture with a 256K context...
Model details →AI21: Jamba Large 1.7 vs Auto Router (Beta)
Auto Router (Beta) wins on 5 of 6 axes — pricing and capability skew in its favour for most workloads.
The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...
Model details →Side-by-side comparison
| Capability | AI21: Jamba Large 1.7 | Auto Router (Beta) | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 2M | 🏆 Auto Router (Beta) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.00 | $-1000000.00 | 🏆 Auto Router (Beta) |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $8.00 | $-1000000.00 | 🏆 Auto Router (Beta) |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | Yes | 🏆 Auto Router (Beta) |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | Yes | 🏆 Auto Router (Beta) |
Frequently asked questions
Is AI21: Jamba Large 1.7 better than Auto Router (Beta)?
Auto Router (Beta) wins on 5 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between AI21: Jamba Large 1.7 and Auto Router (Beta)?
Input: $2.00 vs $-1000000.00 per 1M tokens. Output: $8.00 vs $-1000000.00 per 1M tokens.
What context windows do AI21: Jamba Large 1.7 and Auto Router (Beta) support?
AI21: Jamba Large 1.7 supports up to 256K tokens. Auto Router (Beta) supports up to 2M tokens.
Do both AI21: Jamba Large 1.7 and Auto Router (Beta) support tool calling?
AI21: Jamba Large 1.7: yes. Auto Router (Beta): yes.