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: DeepSeek V4 Pro 0813 is 60% cheaper than DeepSeek: DeepSeek V3.2 Speciale
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
DeepSeek: DeepSeek V4 Pro 0813 is 150% cheaper
| Spec | DeepSeek: DeepSeek V3.2 Speciale | DeepSeek: DeepSeek V4 Pro 0813 |
|---|---|---|
| Provider | deepseek | deepseek |
| Input price / 1M tokens | $0.29 | $0.12 |
| Output price / 1M tokens | $0.43 | $4.00 |
| Context window | 164k tokens | 1049k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
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.