DeepSeek-V3.2-Speciale API
About
Build advanced reasoning agents with DeepSeek-V3.2-Speciale, a specialized AI model optimized for complex logic and chain-of-thought tasks. This model delivers cost-effective pricing at $0.58/1M input and $1.68/1M output tokens, open weights architecture. Access DeepSeek-V3.2-Speciale via the Azure Cognitive Services API with up to 128K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
Yes
Structured Output
No
Tool Use
No
WeightsOpen
Limits
Context Window
128K
Tokens
Input Limit
128K
Tokens
Max Output
128K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.58
Output
$1.68
Frequently Asked Questions
DeepSeek-V3.2-Speciale by Azure Cognitive Services costs $0.58 per 1M input tokens and $1.68 per 1M output tokens.
Model Details
ID
deepseek-v3.2-speciale
Provider
Azure Cognitive ServicesFamily
deepseek
Release Date
Dec 1, 2025
Knowledge Cutoff
Jul 1, 2024
API Integration
NPM Package
@ai-sdk/azure
Environment Variables
AZURE_COGNITIVE_SERVICES_RESOURCE_NAME
AZURE_COGNITIVE_SERVICES_API_KEY