The AI arena is free today

Open Playground
DeepSeekReleased on Dec 13, 2024

DeepSeek VL2 Tiny: API Pricing, Context Window & Benchmarks

DeepSeek VL2 Tiny is a language model from DeepSeek, released in December 2024, with multimodal input.

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

DeepSeek VL2 Tiny benchmarks

Rankings

Quality Tracker

DeepSeek VL2 Tiny Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

LLM Stats Logollm-stats.com - Thu Aug 06 2026
Notice missing or incorrect data?

DeepSeek VL2 Tiny API

Available from the model provider

DeepSeek VL2 Tiny has an official provider API. It is not currently routed through the LLM Stats gateway.

Read the official API documentation

DeepSeek VL2 Tiny latency

DeepSeek VL2 Tiny time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

DeepSeek VL2 Tiny examples

Recent arena outputs from DeepSeek VL2 Tiny, picked from the highest-ranked matchups.

DeepSeek VL2 Tiny license

DeepSeek VL2 Tiny is a proprietary model available under its provider's product and API terms, has 3.0B parameters.

License
deepseek
Hosted access
Parameters
3.0B

DeepSeek VL2 Tiny resources

Official sources for DeepSeek VL2 Tiny: api documentation, official playground, paper or system card, source repository.

DeepSeek VL2 Tiny vs other models

The most-compared alternatives to DeepSeek VL2 Tiny are Grok-1.5V, Llama 3.2 90B Instruct, Phi-3.5-vision-instruct. Open any pair side-by-side for benchmarks, pricing, context, and latency.

Models like DeepSeek VL2 Tiny

Models ranked just above and below DeepSeek VL2 Tiny by LLM Stats score.

 

Grok-1.5V

Score pending
 

Llama 3.2 90B Instruct

Score pending
 

Phi-3.5-vision-instruct

Score pending
 

Grok-1.5

Score pending
 

Llama 3.2 11B Instruct

Score pending
 

Gemini 1.5 Flash 8B

Score pending

FAQ

Common questions about DeepSeek VL2 Tiny.

When was DeepSeek VL2 Tiny released?

DeepSeek VL2 Tiny was released on December 13, 2024 by DeepSeek. This is the official DeepSeek VL2 Tiny release date tracked on LLM Stats.

Is DeepSeek VL2 Tiny available via API?

Yes, DeepSeek VL2 Tiny is available via API. See the official documentation for authentication and endpoint details.

How big is DeepSeek VL2 Tiny?

DeepSeek VL2 Tiny has 3 billion parameters.

Who created DeepSeek VL2 Tiny?

DeepSeek VL2 Tiny was created by DeepSeek.

What is the license for DeepSeek VL2 Tiny?

DeepSeek VL2 Tiny is released under the deepseek license.

Is DeepSeek VL2 Tiny multimodal?

Yes, DeepSeek VL2 Tiny is multimodal and can accept both text and images as input.

Where is the DeepSeek VL2 Tiny paper or technical report?

DeepSeek VL2 Tiny has a paper or technical report available at https://arxiv.org/pdf/2412.10302. Use that source for architecture, training, release and evaluation details.

What models should I compare DeepSeek VL2 Tiny against?

Common DeepSeek VL2 Tiny comparisons include DeepSeek VL2 Tiny vs Grok-1.5V, DeepSeek VL2 Tiny vs Llama 3.2 90B Instruct, DeepSeek VL2 Tiny vs Phi-3.5-vision-instruct. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.