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.
⚡deepseek-ai/DeepSeek-V3.2 is 16ms faster than DeepSeek: DeepSeek V3
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
| Spec | DeepSeek: DeepSeek V3 | deepseek-ai/DeepSeek-V3.2 |
|---|---|---|
| Provider | deepseek | deepseek-ai |
| Input price / 1M tokens | Free | Free |
| Output price / 1M tokens | — | — |
| Context window | 131k tokens | — |
| Latency (p50) | 16ms | — |
| Best benchmark score | — | — |
| Open source | No | Yes |
DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...
deepseek-ai/DeepSeek-V3.2 is a text generation model on Hugging Face with ~2,756,798 monthly downloads. Open access.
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.