deepseek

DeepSeek: DeepSeek V4.1 Flash (batch)

The DeepSeek V4.1 Flash is a batch-oriented AI model that supports both text and image input modalities. It can handle long context lengths of up to 1048576 tokens and provides outputs with a maximum token count of 131072. The model also offers support for tools, reasoning, but does not produce structured output. For those on a budget or seeking a balance between cost and performance, DeepSeek V4.1 Flash may be worth considering. Its pricing model charges $0.112 per million input tokens and $0.336 per million output tokens. Although the available benchmark data is limited to one score with a blended benchmark of 66.3, it is a starting point for evaluation.

Quality Score
100/100
price + capability + benchmarks
Input Price
$0.11
per 1M tokens · checked 2026-09-23
Output Price
$0.34
per 1M tokens · checked 2026-09-23
Context Window
1,048,576
tokens

Benchmark results

Independent, published benchmarks. Blended score 66.3 across 1 benchmark, last refreshed 2026-09-23. How scoring works →

BenchmarkMeasuresScore
AI Index broad capability composite 65.1
Model ID
deepseek/deepseek-v4.1-flash:batch
Vendor
deepseek
Released
September 2026
Tokenizer
DeepSeek
Input Modalities
text, image
Output Modalities
text
Max Output
131,072 tokens
Tool Calling
✓ supported
Structured Output
✓ supported
Reasoning Mode
✓ supported
Vision
✓ accepts images
Audio
no
Moderated
no

What it costs in practice

Computed from the current $0.11/M input and $0.34/M output rates. Run your own numbers →

JobTokensCost
Summarize a 50-page report 30k in / 1.5k out under $0.01
Classify 1,000 customer emails 500k in / 50k out $0.07
A month of a busy support chatbot 5M in / 2M out $1.23

Strong choice for

Category rankings

Where DeepSeek: DeepSeek V4.1 Flash (batch) places across the 19 categories it ranks in. How we rank →

#CategoryScore
#5 Image CaptioningVision · of 25 ranked 121
#5 Real-Time ChatLatency · of 25 ranked 118
#8 Short-Form SummarizationWriting · of 25 ranked 127
#8 Email DraftingWriting · of 25 ranked 123
#8 Language LearningEducation · of 25 ranked 123
#8 Chat CompanionPersonal · of 25 ranked 127
#11 Trivia & General KnowledgePersonal · of 25 ranked 117
#11 Self-Hosted / LocalCost · of 25 ranked 117
#13 Sales / Cold EmailBusiness · of 25 ranked 119
#13 Job Application DraftingBusiness · of 25 ranked 119
#13 Journaling HelperPersonal · of 25 ranked 119
#13 Recipe GenerationPersonal · of 25 ranked 119
#14 Code CompletionCode · of 25 ranked 133
#16 Cheap Bulk InferenceCost · of 25 ranked 137
#20 Bulk Data LabelingData · of 25 ranked 129
#21 Social Media PostsWriting · of 25 ranked 119
#21 Voice Assistant BackendVoice · of 25 ranked 123
#21 Dataset AnnotationResearch · of 25 ranked 133
#25 Resume WritingBusiness · of 25 ranked 113

Similar models

Quick answers

How much does DeepSeek: DeepSeek V4.1 Flash (batch) cost?
$0.11 per million input tokens and $0.34 per million output tokens.
What is DeepSeek: DeepSeek V4.1 Flash (batch)'s context window?
1,048,576 tokens, roughly 1,572 pages of text in a single request.
Does DeepSeek: DeepSeek V4.1 Flash (batch) support tool calling?
It supports tool calling, structured output, a reasoning mode.
Can DeepSeek: DeepSeek V4.1 Flash (batch) process images?
Yes, it accepts image input.

The Model Movers Report

One email every Friday, built from this site's own rankings: the current top five by benchmark score, every model released in the last seven days, and one note worked out from that week's numbers. You can unsubscribe from any issue with one click.