DeepSeek V3.2

by DeepSeek · deepseek/deepseek-v3.2

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...

Input / 1M tokens
$0.26
Output / 1M tokens
$0.38
Context
164K

Specs

Input price$0.26 / 1M tokens
Output price$0.38 / 1M tokens
Cached input$0.13 / 1M tokens
Context window164K tokens
Max output147K tokens
Readstext
Writestext
Tool callingYes
ReasoningYes
ListedDec 1, 2025

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

9 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
GMICloudCheapestFastestfp8164K147K$0.209$0.31$0.0216100%1.55 s51 tok/sNormal
AtlasCloudfp8164K147K$0.26$0.38$0.13100%3.96 s18 tok/sNormal
DeepInfrafp4164K147K$0.26$0.38$0.13100%776 ms23 tok/sNormal
Baidufp8131K65.5K$0.28$0.42$0.028———Normal
SiliconFlowfp8164K147K$0.259$0.80$0.14100%2.14 s17 tok/sNormal
DigitalOcean—164K147K$0.30$0.96$0.09100%1.45 s18 tok/sNormal
Phala—164K64K$1.00$1.00$0.50100%2.48 s25 tok/sNormal
Mara—32.8K7.17K$3.00$4.50——6.46 s21 tok/sNormal
SambaNova—32.8K7.17K$3.00$4.50—100%6.15 s31 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.