LLM Reference

DeepSeek V4 Flash Vision Exp

Released
2026-08-21
Last refreshed
2026-08-24
Status
Researched 1d ago
ProprietaryCommercial use: conditionalMultimodalRAGAgentsLong contextVisionJSON / Tool use

DeepSeek V4 Flash Vision Exp is worth evaluating for rag, agents, and long context when its provider route and context window match the workload.

Use it for

  • Teams evaluating rag, agents, and long context
  • Workloads that can use a 1m context window
  • Buyers comparing 1 tracked provider route

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2026-08-21
Context
1m
Max output
384,000
Architecture
Mixture of Experts
Specialization
vision
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Created by

Advancing artificial general intelligence (AGI).

Hangzhou, Zhejiang, China
Founded 2023
Website
Pricing
Output / 1M
$0.660
Input / 1M
$0.220

Cheapest of 1 route · DeepSeek Platform · cache read $0.007

About

DeepSeek V4 Flash Vision Exp is DeepSeek's experimental multimodal extension of V4 Flash, released August 21, 2026. It matches V4 Flash on text while adding image understanding for agent workflows through the DeepSeek API model ID deepseek-v4-flash-vision-exp. Images are billed as up to 384 input tokens each at V4 Flash text rates. Experimental public API; weights not released.

Top use-case fit: coding, agents, and build tasks

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Long context

Included by capability and metadata signals in the decision map.

Capabilities

VisionMultimodalReasoningJSON / Tool useStructured OutputsPrompt Caching

Benchmark peer barsfor RAG

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.

API versions

deepseek-v4-flash-vision-exp