Deepseek v3.2 API
About
Integrate multimodal vision capabilities using Deepseek v3.2, designed to process both text and images seamlessly. This model delivers available completely free of charge, native tool calling support, open weights architecture. Access Deepseek v3.2 via the Kiro API with up to 64K output tokens.
Capabilities
Input Modalities
textimage
Output Modalities
text
Reasoning
No
Structured Output
No
Tool Use
Yes
WeightsOpen
Temperature
Adjustable
Attachment
Supported
Limits
Context Window
164K
Tokens
Input Limit
164K
Tokens
Max Output
64K
Tokens
Pricing
Standard (per 1M tokens)
Input
Free
Output
Free
Frequently Asked Questions
Deepseek v3.2 by Kiro costs Free per 1M input tokens and Free per 1M output tokens.
Model Details
API Integration
NPM Package
kiro-acp-ai-provider
Environment Variables
KIRO_API_KEY
API Base URL
https://q.us-east-1.amazonaws.com