LLM Reference

DeepSeek V3.1

Multimodal

About

Enhanced reasoning and grounded retrieval model from DeepSeek with multimodal text and image understanding.

Capabilities

MultimodalFunction CallingTool UseJSON Mode

Providers(1)

ProviderInput (per 1M)Output (per 1M)Type
Microsoft FoundryServerlessProvisioned

Specifications

Released2026-03-01
ArchitectureMixture of Experts
Specializationgeneral