DeepSeek V3.1

by DeepSeek · deepseek/deepseek-chat-v3.1

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...

Input / 1M tokens
$0.25
Output / 1M tokens
$0.95
Context
164K

Specs

Input price$0.25 / 1M tokens
Output price$0.95 / 1M tokens
Cached input$0.13 / 1M tokens
Context window164K tokens
Max output147K tokens
Readstext
Writestext
Tool callingYes
ReasoningYes
ListedAug 21, 2025

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

Providers

5 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
DeepInfraCheapestfp4164K147K$0.25$0.95$0.13100%1.02 s12 tok/sNormal
SiliconFlowfp8164K147K$0.27$1.00—100%1.79 s20 tok/sNormal
SambaNovafp8131K7.17K$0.65$1.50——3.32 s36 tok/sNormal
CoreWeavefp8161K145K$0.55$1.65$0.55100%244 ms85 tok/sNormal
MaraFastest—131K118K$0.60$1.70—96.7%1.15 s90 tok/sCode -2

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