← model directory
deepseek
DeepSeek: DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp
↓ runs free on your own hardwareDeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attention (DSA), a fine-grained sparse attention mechanism...
specs & pricing
- Type
- text
- Provider
- deepseek
- Model ID
- deepseek/deepseek-v3.2-exp
- Capabilities
- tools, reasoning
- Context window
- 164K tokens
- Self-hostable
- Yes — runs on your own GPU
- Input price
- $0.30 / 1M tokens
- Output price
- $0.45 / 1M tokens
Cloud price is billed from prepaid credits when a request fails over to the cloud. Open-weight models run free on GPUs you own — the gateway routes to your nodes first.