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-4o (2024-05-13) is 83% cheaper than OpenAI: GPT-4 (older v0314)
⚡OpenAI: GPT-4 (older v0314) is 18ms faster than OpenAI: GPT-4o (2024-05-13)
📈OpenAI: GPT-4 (older v0314) scores 1270.0 pts higher on benchmarks
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
OpenAI: GPT-4o (2024-05-13) is 500% cheaper
| Spec | OpenAI: GPT-4 (older v0314) | OpenAI: GPT-4o (2024-05-13) |
|---|---|---|
| Provider | openai | openai |
| Input price / 1M tokens | $30.00 | $5.00 |
| Output price / 1M tokens | $60.00 | $15.00 |
| Context window | 8k tokens | 128k tokens |
| Latency (p50) | — | 18ms |
| Best benchmark score | 1270.0 | — |
| Open source | No | No |
GPT-4-0314 is the first version of GPT-4 released, with a context length of 8,192 tokens, and was supported until June 14. Training data: up to Sep 2021.
GPT-4o ("o" for "omni") is OpenAI's latest AI model, supporting both text and image inputs with text outputs. It maintains the intelligence level of [GPT-4 Turbo](/models/openai/gpt-4-turbo) while being twice as...
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.