All Models
DeepSeek V3.2 Speciale
DeepSeek-V3.2-Speciale is a high-compute variant of DeepSeek-V3.2 optimized for maximum reasoning and agentic performance. It builds on DeepSeek Sparse Attention (DSA) for efficient long-context processing, then scales post-training reinforcement learning...
Available Providers (4)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 OpenRouter | deepseek/deepseek-v3.2-speciale | $0.27/MTok | $0.41/MTok | 163.8K | 65.5K | |
 NanoGPT | deepseek/deepseek-v3.2-speciale | $0.28/MTok | $0.42/MTok | 163K | 65.5K | |
 Azure Cognitive Services | deepseek-v3.2-speciale | $0.58/MTok | $1.68/MTok | 128K | 128K | |
 Azure | deepseek-v3.2-speciale | $0.58/MTok | $1.68/MTok | 128K | 128K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output