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.
💰gpt-3.5-turbo-0125 is 100% cheaper than OpenAI: GPT-5 Codex
⚡OpenAI: GPT-5 Codex is 783ms faster than gpt-3.5-turbo-0125
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
OpenAI: GPT-5 Codex is 2175% faster
| Spec | gpt-3.5-turbo-0125 | OpenAI: GPT-5 Codex |
|---|---|---|
| Provider | openai | openai |
| Input price / 1M tokens | Free | $1.25 |
| Output price / 1M tokens | — | $10.00 |
| Context window | — | 400k tokens |
| Latency (p50) | 819ms | 36ms |
| Best benchmark score | — | — |
| Open source | No | No |
This cost-effective large language model excels at conversational tasks, content generation, and general-purpose text processing, making it ideal for developers and businesses seeking a balance between capability and affordability for production applications.
GPT-5-Codex is a specialized version of GPT-5 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, independent execution of complex engineering tasks....
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.