Loading...
Loading...
Side-by-side comparison of API pricing, context window, latency, and benchmark performance. Data refreshed daily from provider APIs and ModelStop's own latency probes.
💰Qwen: Qwen2.5 Coder 7B Instruct is 99% cheaper than AI21 Jamba 1.6 Large
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Qwen: Qwen2.5 Coder 7B Instruct is 6567% cheaper
| Spec | AI21 Jamba 1.6 Large | Qwen: Qwen2.5 Coder 7B Instruct |
|---|---|---|
| Provider | ai21 | qwen |
| Input price / 1M tokens | $2.00 | $0.03 |
| Output price / 1M tokens | $8.00 | $0.09 |
| Context window | 256k tokens | 33k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
AI21 Jamba 1.6 Large uses a hybrid Mamba-Transformer architecture offering low memory footprint and high throughput compared to equivalent Transformer models. Features 256K context at a fraction of the inference cost.
Qwen2.5-Coder-7B-Instruct is a 7B parameter instruction-tuned language model optimized for code-related tasks such as code generation, reasoning, and bug fixing. Based on the Qwen2.5 architecture, it incorporates enhancements like RoPE,...
Want to swap in a different model or estimate monthly costs?