Use DePlot for Free

DePlot is an AI model released 2023 by google, a leading organization in large language model research. Google DePlot — translates a chart or plot image into a structured table of underlying numbers. Pair with an LLM for chart Q&A. With a large number of parameters and a a large context window context window, DePlot is designed to excel across a range of demanding tasks — from software engineering and mathematical problem-solving to multilingual content generation and long-document analysis.

DePlot uses a dense transformer architecture with a large number of parameters of parameters, all of which are active for every input token. Dense architectures provide predictable, consistent behavior across diverse task types — there are no "cold" experts to warm up, and quality is uniform across prompts. google's training pipeline combined large-scale pretraining on a large-scale multilingual pretraining dataset with supervised fine-tuning and alignment techniques (RLHF or DPO), producing DePlot's characteristic balance of capability, helpfulness, and safety.

As of 2026-10-16, DePlot by google demonstrates measurable performance on standard AI evaluation benchmarks. On ChartQA — which measures model performance on specialized evaluation tasks — it achieves 24.0% improvement over baseline. These scores place DePlot in a competitive position within its model class. Note that benchmark scores reflect controlled evaluation conditions; real-world performance varies by task, prompt design, and domain specificity.

The primary strengths of DePlot are: Chart and figure understanding: converts plots to tables for LLM reasoning; Apache 2.0 — free; Enables any LLM to reason about charts and graphs. These make it particularly well-suited for Chart data extraction for automated reporting, Financial chart analysis, Scientific figure understanding in research pipelines. Users working on complex, multi-step problems benefit most from DePlot's ability to maintain coherence across long inputs and produce structured, verifiable outputs.

Like all current AI systems, DePlot has limitations: Two-step process: DePlot extracts table, then LLM reasons — adds latency. For production deployments, validating outputs against authoritative sources — especially for domain-specific or time-sensitive information — remains best practice. google continues to improve DePlot through ongoing research.

DePlot is available on LITHOVEX AI with a free account. Unlike direct API access — which requires billing setup, API key management, and per-token charges — LITHOVEX AI provides a seamless browser interface with no setup required, making DePlot accessible to students, researchers, developers, and early-stage teams globally.

As of 2026-10-16, DePlot by google demonstrates measurable performance on standard AI evaluation benchmarks. On ChartQA — which measures model performance on specialized evaluation tasks — it achieves 24.0% improvement over baseline. These scores place DePlot in a competitive position within its model class. Note that benchmark scores reflect controlled evaluation conditions; real-world performance varies by task, prompt design, and domain specificity.

DePlot: one-shot visual language reasoning for chart-to-table understanding

The training pipeline for DePlot involves multiple stages: large-scale pretraining on diverse multilingual text and code corpora to develop broad world knowledge, followed by supervised fine-tuning on instruction-response pairs, and alignment techniques such as RLHF or DPO. Each stage refines the model's helpfulness, accuracy, and safety. google's research team — based in United States — has optimized DePlot for the specific capability profile described above.

Inference efficiency: DePlot is designed to deliver quality outputs at practical serving speeds. Its context capacity supports complex multi-turn conversations without quality degradation.

Getting started with DePlot on LITHOVEX AI takes under two minutes. Follow these steps:

For best results with DePlot: provide specific, context-rich prompts; include examples when generating code; specify output format when structure matters; break complex tasks into focused sub-questions.

Google DeepMind is Alphabet's AI research organization, formed through the merger of Google Brain and DeepMind in 2023. Google published the original "Attention Is All You Need" paper in 2017, which introduced the transformer architecture underlying virtually every modern language model. The Gemma model family represents Google's open-weight contributions — models that bring Google research quality to open-access deployment. Gemma 3 and Gemma 4 models support multimodal inputs including images and long-document processing. Google's computational infrastructure and proprietary TPUs give it advantages in training efficiency that few organizations can match.

Funding: Part of Alphabet Inc. ($1.9T+ market cap)

Founded: 1998, headquartered in United States.

Visit the official google website →

DePlot by google competes in a field with several strong alternatives. Below is a detailed side-by-side comparison against commonly listed alternatives, using benchmark data and capability profiles in the catalog.

Both DePlot and the models above are available free on LITHOVEX AI — test them side by side on your real tasks before committing to a subscription with any provider.

DePlot is released under Apache 2.0, which means you can download and run it on your own hardware. Below are the quickest ways to get started.

Data visualization parsing is a critical global need for business intelligence, research, and journalism. Financial charts in annual reports, scientific data plots in papers, and business graphs in presentations all contain data that DePlot can extract into structured tables for analysis.

DePlot by google has the following version history and notable updates:

For the complete changelog and latest release notes, visit the official google model page.