DeepSeek v3.2 Exp
Review DeepSeek v3.2 Exp on key metrics including price, context length, throughput, and model features.
AuthorDeepseek
Context Length163.8k
Supports Tools
DeepSeek-V3.2-Exp is an experimental large language model from DeepSeek, serving as an intermediate step between V3.1 and future architectures. It features DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism that enhances training and inference efficiency for long-context tasks while preserving high output quality.
Activity
Last 14 daysPrompt
15MCompletion
2MTotal
17MStartup
Startup
Latency (p50)-
Throughput (p50)17.2 tok/s
Pricing
Input$0.14/M tokens
Output$0.20/M tokens
Features
Input Modalitiestext
Output Modalitiestext
Supported EndpointsChat Completions
Vision
Supports Tools