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 window, it delivers more acc…
Model details →AI21: Jamba Large 1.7 vs Relace: Relace Search
Relace: Relace Search wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search performs agentic multi-step reasoning to produce highly prec…
Model details →Side-by-side comparison
| Capability | AI21: Jamba Large 1.7 | Relace: Relace Search | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 256K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.00 | $1.00 | 🏆 Relace: Relace Search |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $8.00 | $3.00 | 🏆 Relace: Relace Search |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is AI21: Jamba Large 1.7 better than Relace: Relace Search?
Relace: Relace Search wins on 2 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 Relace: Relace Search?
Input: $2.00 vs $1.00 per 1M tokens. Output: $8.00 vs $3.00 per 1M tokens.
What context windows do AI21: Jamba Large 1.7 and Relace: Relace Search support?
AI21: Jamba Large 1.7 supports up to 256K tokens. Relace: Relace Search supports up to 256K tokens.
Do both AI21: Jamba Large 1.7 and Relace: Relace Search support tool calling?
AI21: Jamba Large 1.7: yes. Relace: Relace Search: yes.