DeepSeek v3.1
DeepSeekBalanced
ThinkingTool UseStructured Output
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...
Performance Tier
Balanced
DeepSeek v3.1 is a balanced model from DeepSeek : strong performance at a reasonable price.
Strong cost-performance ratio. Reliable for most professional use cases without premium pricing.
Pricing
This model is included in Elosia plansAffordable
Low cost. Suitable for sustained use and high-volume interactions.
| Type | per 1M tokens |
|---|---|
| Input (prompt) | $0.210 |
| Output (completion) | $0.790 |
| Cache read | $0.130 |
Capabilities
Context Length164K
Max Output Tokens33K
TokenizerDeepSeek
Inputtext
Outputtext
Release DateAugust 21, 2025
Benchmarks
General Intelligence
MMLU
87.5%
GPQA Diamond
72.8%
Mathematics
MATH-500
89.2%
Programming
HumanEval
89%
Recommended Use Cases
CodingMathematicsAnalysisGeneral Chat
Strengths
- Strong math and coding performance at a very low price
- Open-weight model enabling self-hosting
- Good general reasoning for its cost tier
Limitations
- Superseded by DeepSeek v3.2 on most benchmarks
- Weaker creative writing compared to proprietary models
Resources
This model may use your data for training
