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-oss-20b is 100% cheaper than OpenAI: GPT-3.5 Turbo
⚡OpenAI: GPT-3.5 Turbo is 126ms faster than gpt-oss-20b
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
OpenAI: GPT-3.5 Turbo is 663% faster
| Spec | gpt-oss-20b | OpenAI: GPT-3.5 Turbo |
|---|---|---|
| Provider | openai | openai |
| Input price / 1M tokens | Free | $0.50 |
| Output price / 1M tokens | — | $1.50 |
| Context window | 128k tokens | 16k tokens |
| Latency (p50) | 145ms | 19ms |
| Best benchmark score | — | — |
| Open source | No | No |
OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases – gpt-oss-20b is for lower latency, and local or specialized use-cases.
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.
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.