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.
💰bge-reranker-base is 100% cheaper than Amazon Titan Text Express
⚡Amazon Titan Text Express is 46ms faster than bge-reranker-base
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | Amazon Titan Text Express | bge-reranker-base |
|---|---|---|
| Provider | amazon | baai |
| Input price / 1M tokens | $0.20 | Free |
| Output price / 1M tokens | $0.60 | — |
| Context window | 8k tokens | — |
| Latency (p50) | — | 46ms |
| Best benchmark score | — | — |
| Open source | No | No |
Amazon Titan Text Express is a generative LLM for summarization, text generation, classification, open-ended Q&A, and information extraction. Optimized for enterprise workloads via AWS Bedrock.
Different from embedding model, reranker uses question and document as input and directly output similarity instead of embedding. You can get a relevance score by inputting query and passage to the reranker. And the score can be mapped to a float value in [0,1] by sigmoid function.
Want to swap in a different model or estimate monthly costs?