DeepSeek
DeepSeek V4.1 Flash (Reasoning, Max Effort)
DeepSeek V4.1 Flash is an AI model from DeepSeek designed for fast, efficient multimodal interactions. It combines native multimodal capabilities with a new architecture focused on stronger performance, faster responses, and lower computational cost.
DeepSeek release notesModel Snapshot
TypeLanguage
ReleaseSep 8, 2026
Context1,048,576
Tagsreasoning, tool-use, implicit-caching, vision
Overall
Rank #60 across 687
39.5
Coding
No rank
n/a
Blended Price
Rank #144 across 432
$0.525/M
Strength Profile
Percentile score by analysis domain.
* Cost is inverted: lower input, output, and blended prices rank higher.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Output Speed230.9 tok/s
First Token0.79s
Max Output943,718
Pricing
Blended$0.525/M
Input$0.300/M
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| Artificial Analysis Intelligence Index | overall | 39.5 | #60 |
| LiveBench Mathematics | math | 93.3% | #16 |
| Humanity's Last Exam | reasoning | 39.2% | #74 |
| SciCode | coding, reasoning | 51.9% | #70 |
| Output Speed |