LLM ReferenceLLM Reference
GCP Vertex AI

DeepSeek V3 on GCP Vertex AI

DeepSeek V3 · DeepSeek

ServerlessOpen Source

Compare DeepSeek V3 Across Providers

ProviderInput (per 1M)Output (per 1M)
DeepInfra$32.00$89.00
Fireworks AI$0.56$1.68
DeepSeek Platform$0.14$0.28
Microsoft Foundry
OpenRouter$0.26$0.38
View all 12 providers →

Pricing

TypePrice (per 1M)
Input tokens$0.75
Output tokens$3.00

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode Execution

About DeepSeek V3

DeepSeek V3: Latest flagship model. 685B total with MoE. 128K context. Open-source.

Get Started

Model Specs

Released2024-12-26
Parameters671B
Context64k
ArchitectureMixture of Experts
Knowledge cutoff2024-04

GPU-Hour Providers(1)

Provider

GCP Vertex AI
GCP Vertex AI

Google Cloud Platform (GCP)

All models on GCP Vertex AI