Deepseek
DeepSeek V4 Flash Vision Exp
DeepSeek-V4-Flash-Vision-Exp is the first experimental multimodal model in the DeepSeek-V4 family. It builds on DeepSeek-V4-Flash by adding visual modules and continued training for visual understanding, with substantially improved multimodal agent capabilities while remaining comparable on text-only agent tasks.
DeepSeek release notesModel Snapshot
TypeLanguage
ReleaseAug 21, 2026
Context1,048,576
Tagsreasoning, tool-use, implicit-caching, vision
Overall
No rank
n/a
Coding
No rank
n/a
Blended Price
No rank
n/a
Strength Profile
Percentile score by analysis domain.
Not enough comparable domain data for this model.
Benchmark Percentiles
Higher bars mean stronger relative placement.
Model Details
Runtime
Max Output943,718
Streaming speed is not measured for this model yet.
Pricing
Blended-
Input-
Output-
Catalog$0.220/M in / $0.660/M out
Metadata
Modalities
All Benchmarks
| Metric | Domain | Value | Rank |
|---|---|---|---|
| LiveBench Mathematics | math | 87.8% | #33 |