AI21 Jamba 1.6 Mini
ai21
AI21 Jamba 1.6 Mini is a lightweight Mamba-Transformer hybrid optimized for cost-effective, high-throughput inference with an impressive 256K context window. An excellent choice for document-heavy workloads on a budget.
- Context window
- 256,000 tokens
- Input cost
- $0.20 / 1M
- Output cost
- $0.40 / 1M
- Latency (p50)
- —