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.
💰Amazon Titan Text Express is 83% cheaper than Qwen2.5 72B Instruct
⚡Amazon Titan Text Express is 380ms faster than Qwen2.5 72B Instruct
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Amazon Titan Text Express is 500% cheaper
| Spec | Amazon Titan Text Express | Qwen2.5 72B Instruct |
|---|---|---|
| Provider | amazon | qwen |
| Input price / 1M tokens | $0.20 | $1.20 |
| Output price / 1M tokens | $0.60 | $1.20 |
| Context window | 8k tokens | 33k tokens |
| Latency (p50) | — | 380ms |
| 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.
This large instruction-tuned language model with 72 billion parameters and 33K token context excels at complex reasoning, detailed analysis, and multi-turn conversations, making it ideal for researchers, developers, and enterprises requiring sophisticated AI capabilities at a cost-effective price point of $1.20 per million input tokens.
Want to swap in a different model or estimate monthly costs?
Help my team choose the right model
Not sure which model fits your workload, budget, and latency requirements? Get a tailored recommendation.