DeepSeek: DeepSeek V3.1
9.1 / 10
163.8K context
Proprietary
About this model
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 base with a two-phase long-context...
Benchmark Scores
MMLU
93.4
MMLU-Pro
85.0
SimpleQA
93.4
AIME-2024
93.1
Technical Specs
- Architecture: text->text
- Context Window: 163,840 tokens
- Input Modalities: text
Hardware Requirements
- API-only (no local hardware needed)
Pricing
| Input | Output | Currency |
|---|---|---|
| 0.55 / 1M tokens | 1.65 / 1M tokens | USD |