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 V4.1 Flash is 96% cheaper than Deepseek V3 0324
Price (lower is better), Speed/Latency (lower is better), Performance (higher is better)
DeepSeek: DeepSeek V4.1 Flash is 2678% cheaper
| Spec | DeepSeek: DeepSeek V4.1 Flash | Deepseek V3 0324 |
|---|---|---|
| Provider | deepseek | deepseek-ai |
| Input price / 1M tokens | $0.04 | $1.25 |
| Output price / 1M tokens | $0.50 | $1.25 |
| Context window | 1049k tokens | 164k tokens |
| Latency (p50) | — | — |
| Best benchmark score | — | — |
| Open source | No | No |
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Deepseek V3 0324 — DeepSeek open-source language model with competitive performance on reasoning and coding benchmarks.
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.