DeepSeekdeepseek-v3.2-exp

DeepSeek: DeepSeek V3.2 Exp API Pricing

DeepSeek-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-g...

Base Input Price$0.27/ 1M tokens

Base Output Price$0.41/ 1M tokens

Prompt Cache Read$0.069-74.48% discount

Batch API RateN/A24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates

Provider Name	Input / 1M	Output / 1M	Prompt Caching	Access Endpoint
DeepSeek Direct	$0.27	$0.41	Supported	Connect
OpenRouter	$0.27	$0.41	Supported	Connect

Head-to-Head Comparisons for DeepSeek: DeepSeek V3.2 Exp

DeepSeek: DeepSeek V3.2 Exp vs OpenAI: GPT-6.1 Sol$0.27/M vs $2/M

DeepSeek: DeepSeek V3.2 Exp vs GPT-4o (Omni)$0.27/M vs $2.5/M

DeepSeek: DeepSeek V3.2 Exp vs Claude 3.5 Sonnet$0.27/M vs $3/M

DeepSeek: DeepSeek V3.2 Exp vs DeepSeek-V3 (deepseek-chat)$0.27/M vs $0.27/M