DeepSeek: DeepSeek V3.2 Speciale
🇨🇳 DeepSeek · DeepSeek V3.2
Overview
DeepSeek: DeepSeek V3.2 Speciale is a large language model API from DeepSeek, part of its DeepSeek V3.2 model family. At $0.287 per million input tokens and $0.431 per million output tokens, it sits in the budget tier — among the cheaper options for high-throughput or cost-sensitive workloads. Output tokens cost about 2× as much as input, so prompt-heavy workloads run noticeably cheaper than generation-heavy ones. The 164K-token context window — around 246 pages of text — comfortably handles long documents, multi-file code, or extended conversations. On Artificial Analysis's Intelligence Index it scores 23 (D grade), a useful proxy for its general reasoning strength relative to the other models tracked here. All prices on this page reflect OpenRouter's routed rates and are re-synced automatically every day; confirm against the provider's official pricing before committing to production.
| Dimension | Unit | Price (USD) |
|---|---|---|
| Input | per 1M tokens | $0.287 |
| Output | per 1M tokens | $0.431 |
| Cached Input | per 1M tokens | $0.058 |
- Provider
- DeepSeek
- Model Family
- DeepSeek V3.2
- Version String
- deepseek/deepseek-v3.2-speciale
- Status
- Active
- Modality
- Text
- Context Window
- 163,840 tokens
- Output Limit
- 163,840 tokens
Index Metrics
Cross-domain capability indexes evaluated by Artificial Analysis — Artificial Analysis
Benchmark Scores
Data source: Artificial Analysis
Key Insights
Key data points from this page for quick reference and citation.
- DeepSeek: DeepSeek V3.2 Speciale Input price: $0.287/M tokens
- DeepSeek: DeepSeek V3.2 Speciale Output price: $0.431/M tokens
- Context window: 163,840 tokens
- Provider: DeepSeek
- Model family: DeepSeek V3.2
- Modalities: Text
- Data source: OpenRouter, updated daily