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.
💰Microsoft: Phi 4 is 65% cheaper than Amazon Titan Text Express
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
Microsoft: Phi 4 is 186% cheaper
| Spec | Amazon Titan Text Express | Microsoft: Phi 4 |
|---|---|---|
| Provider | amazon | microsoft |
| Input price / 1M tokens | $0.20 | $0.07 |
| Output price / 1M tokens | $0.60 | $0.14 |
| Context window | 8k tokens | 16k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | Yes |
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.
[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...
Want to swap in a different model or estimate monthly costs?