All Models
DeepSeek V3.2 (ByteDance)
DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
Benchmarks
Available Providers (1)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 LLM Gateway | bytedance/deepseek-v3.2 | $0.28/MTok | $0.42/MTok | 131.1K | 32.8K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output