DeepSeek VL2
Overview
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.
DeepSeek VL2 was released on December 13, 2024. API access is available through Replicate.
Performance
Timeline
ReleasedUnknown
Knowledge CutoffUnknown
Specifications
Parameters
27.0B
License
deepseek
Training Data
Unknown
Benchmarks
DeepSeek VL2 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Mon Jan 19 2026Notice missing or incorrect data?Start an Issue discussion→
Pricing
Pricing, performance, and capabilities for DeepSeek VL2 across different providers:
| Provider | Input ($/M) | Output ($/M) | Max Input | Max Output | Latency (s) | Throughput | Quantization | Input | Output |
|---|---|---|---|---|---|---|---|---|---|
 Replicate | $9.50 | $4800.00 | 129.3K | 129.3K | 0.5 | 22.0 c/s | — | Text Image Audio Video | Text Image Audio Video |
API Access
API Access Coming Soon
API access for DeepSeek VL2 will be available soon through our gateway.
Recent Posts
Recent Reviews
FAQ
Common questions about DeepSeek VL2
DeepSeek VL2 was released on December 13, 2024.
DeepSeek VL2 has 27.0 billion parameters.