Model comparison
DeepSeek V3 vs DeepSeek V3.1
Compare DeepSeek V3 and DeepSeek V3.1: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
DeepSeek
DeepSeek V3
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 tok
DeepSeek
DeepSeek V3.1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 ba
| Metric | DeepSeek V3 | DeepSeek V3.1 |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Context window | 131,072 | 163,840 |
| Input $/Mtok | $0.200 | $0.210 |
| Output $/Mtok | $0.800 | $0.790 |
| Modalities | text | text |
| License | open-weights | open-weights |
Quick take
On input price, DeepSeek V3 is cheaper at $0.200/Mtok. For context window, DeepSeek V3.1 leads with 163,840 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.