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.
💰OpenAI: GPT-3.5 Turbo is 60% cheaper than OpenAI: GPT-5 Codex
⚡OpenAI: GPT-3.5 Turbo is 17ms faster than OpenAI: GPT-5 Codex
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
OpenAI: GPT-3.5 Turbo is 150% cheaper
OpenAI: GPT-3.5 Turbo is 89% faster
| Spec | OpenAI: GPT-3.5 Turbo | OpenAI: GPT-5 Codex |
|---|---|---|
| Provider | openai | openai |
| Input price / 1M tokens | $0.50 | $1.25 |
| Output price / 1M tokens | $1.50 | $10.00 |
| Context window | 16k tokens | 400k tokens |
| Latency (p50) | 19ms | 36ms |
| Best benchmark score | — | — |
| Open source | No | No |
GPT-3.5 Turbo is OpenAI's fastest model. It can understand and generate natural language or code, and is optimized for chat and traditional completion tasks. Training data up to Sep 2021.
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.