DeepSeek
DeepSeek
MultimodalAUTO PROFILELIVE PRICING

DeepSeek V4 Flash Vision Exp (batch)

text+image->text

DeepSeek V4 Flash Vision Exp (batch) is a vision-language model that takes images alongside text, built for OCR, diagram understanding, and multi-modal reasoning. Available via DeepSeek. 1,048,576-token context. Budget pricing.

DeepSeek V4 Flash Vision Exp (batch) is a multimodal AI model from DeepSeek. It costs $0.110 per million input tokens and $0.330 per million output tokens (blended $0.176/M), with a 1,048,576-token context window.

INPUT
$0.110/M
per million input tokens
OUTPUT
$0.330/M
per million output tokens
BLENDED 70/30
$0.176/M
unchanged since 3 May
CONTEXT
1,048,576
tokens
What it is good at
  • OCR & document understanding
  • Diagram and chart interpretation
  • Multi-image reasoning
  • Visual question answering
Typical use cases
  • Document Q&A
  • Receipt/form extraction
  • Chart-to-data
  • Accessibility descriptions

Benchmarks

No published benchmark scores tracked for this model yet. Frontier and reasoning models from major providers have scores; smaller models and inference-host variants typically inherit the underlying open-weights score.

More from DeepSeek

See all 11

Frequently asked questions

How much does DeepSeek V4 Flash Vision Exp (batch) cost?

DeepSeek V4 Flash Vision Exp (batch) costs $0.110 per million input tokens and $0.330 per million output tokens, for a blended reference rate of $0.176 per million tokens.

What is DeepSeek V4 Flash Vision Exp (batch)'s context window?

DeepSeek V4 Flash Vision Exp (batch) supports up to 1,048,576 tokens of context in a single request.

What is DeepSeek V4 Flash Vision Exp (batch) best for?

DeepSeek V4 Flash Vision Exp (batch) is well suited to OCR & document understanding, Diagram and chart interpretation and Multi-image reasoning.

Who makes DeepSeek V4 Flash Vision Exp (batch)?

DeepSeek V4 Flash Vision Exp (batch) is developed and served by DeepSeek.

Terms used on this page