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 is 100% cheaper than OpenAI: GPT-4 Turbo (older v1106)
⚡OpenAI: GPT-4 Turbo (older v1106) is 787ms faster than gpt-3.5-turbo
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | gpt-3.5-turbo | OpenAI: GPT-4 Turbo (older v1106) |
|---|---|---|
| Provider | openai | openai |
| Input price / 1M tokens | Free | $10.00 |
| Output price / 1M tokens | — | $30.00 |
| Context window | 16k tokens | 128k tokens |
| Latency (p50) | 787ms | — |
| Best benchmark score | — | — |
| Open source | No | No |
OpenAI's lightweight and fast GPT-3.5 Turbo — cost-effective for most applications.
The latest GPT-4 Turbo model with vision capabilities. Vision requests can now use JSON mode and function calling. Training data: up to April 2023.
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.