DeepSeek V3.2 API
About
Process massive datasets with DeepSeek V3.2, featuring an expansive 128K context window for long-document analysis. This model delivers cost-effective pricing at $0.28/1M input and $0.42/1M output tokens, open weights architecture. Access DeepSeek V3.2 via the Vercel AI Gateway API with up to 8K output tokens.
Capabilities
Input Modalities
text
Output Modalities
text
Reasoning
No
Structured Output
Yes
Tool Use
No
WeightsOpen
Temperature
Adjustable
Attachment
Not Supported
Limits
Context Window
128K
Tokens
Input Limit
128K
Tokens
Max Output
8K
Tokens
Pricing
Standard (per 1M tokens)
Input
$0.28
Output
$0.42
Caching (per 1M tokens)
Read
$0.03
Frequently Asked Questions
DeepSeek V3.2 by Vercel AI Gateway costs $0.28 per 1M input tokens and $0.42 per 1M output tokens. Cached reads cost $0.03 per 1M tokens.
Model Details
ID
deepseek/deepseek-v3.2
Provider
Vercel AI GatewayFamily
deepseek
Release Date
Dec 1, 2025
Knowledge Cutoff
Jul 1, 2024
API Integration