DeepSeek model product
An advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding.
Updated Aug 10, 2026. Default version: DeepSeek VL2 Tiny
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version DeepSeek VL2 Tiny.
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
The default version has no provider offering with current input or output token prices.
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| DeepSeek VL2 | N/A | 27B | 129.3K | 129.3K | No | deepseek | |
| DeepSeek VL2 Small | N/A | 16B | N/A | N/A | No | deepseek | |
| DeepSeek VL2 Tiny | 0.0 | 3B | N/A | N/A | No | deepseek |
A concise description based on the published model registry.
An advanced series of large Mixture-of-Experts (MoE) Vision-Language Models that significantly improves upon its predecessor, DeepSeek-VL. DeepSeek-VL2 demonstrates superior capabilities across various tasks, including but not limited to visual question answering, optical character recognition, document/table/chart understanding, and visual grounding.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about DeepSeek-VL2.
DeepSeek-VL2's default version was released on Dec 13, 2024.
No official standard PAYG price is currently available for DeepSeek-VL2.
DeepSeek-VL2 is published under DeepSeek in the model registry.
The current registry does not publish a context window for the default version.
No. The default version is not marked as having publicly available weights.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include Command R+, Gemini 1.5 Flash 8B, Gemma 2 27B.