Model reference · open weights

DeepSeek-Flash-Vision-Exp

Available as managed deployment NEW · this week LLMs unsloth Text gen 1 variants 0 dl/mo

DeepSeek-Flash-Vision-Exp is an open-weight language model from unsloth. AxForge deploys and operates it for you on dedicated EU-owned hardware — with the licence handled where one is required.

Available as managed deployment — configured and operated for you on dedicated EU hardware, quoted per deployment.

What it is

Makerunsloth
TypeLanguage models
TaskText gen
Parameters (lead)304.6B
Context1024k tokens
Runs withtransformers
Based ondeepseek-ai/DeepSeek-V4-Flash-Vision-Exp
Released2026-08-31
Popularity0 downloads / month
LicenceOpen weights

About

What DeepSeek-Flash-Vision-Exp is

Introduction

We are excited to introduce DeepSeek-V4-Flash-Vision-Exp, our first experimental multimodal model in the DeepSeek-V4 family. It builds on the DeepSeek-V4-Flash architecture by incorporating visual modules and undergoing continued training to unlock visual understanding capabilities.

Compared to DeepSeek-V4-Flash-0731, DeepSeek-V4-Flash-Vision-Exp achieves substantial improvements on its multimodal agent capabilities, while maintaining comparable performance on text-only agent tasks.

BenchmarkDeepSeek-V4-Flash-Vision-ExpDeepSeek-V4-Flash-0731Opus-4.8
Text Agent Capabilities
Terminal Bench 2.183.982.785.0
NL2Repo57.754.269.7
Cybergym75.376.778.3
DeepSWE59.354.458.0
Toolathlon-Verified75.970.376.2
DSBench-Hard63.659.671.7
AutomationBench (Public)25.725.127.2
Multimodal Agent Capabilities
ApexBench (Pass@1)36.526.2†39.4
Agents' Last Exam27.325.2†25.7
Chartography64.3-65.0
ZeroBench (Pass@5)35.0-34.0

Notes:

  1. For the text agent benchmarks above, DeepSeek models are evaluated with the minimal mode of DeepSeek Harness as the agent framework, using the max reasoning effort level with temperature = 1.0, top_p = 0.95.
  2. † For ApexBench and Agents' Last Exam, DeepSeek-V4-Flash-0731 ignores the multimodal elements in the input.

Repository layout

This repository contains the tokenizer, prompt encoding reference, and a minimal PyTorch inference implementation for DeepSeek-V4 Flash Vision. The reference inference covers the vision encoder and aligner, DFlash attention, MoE, Hyper-Connections, and the DSpark forward path.

.
├── encoding/                  # OpenAI-style messages -> model prompt
├── inference/                 # weight conversion and minimal inference
│   └── examples/              # equivalent TXT and JSON vision prompts
├── config.json                # Hugging Face model metadata
├── generation_config.json
├── model.safetensors.index.json
├── tokenizer.json
└── tokenizer_config.json

encoding/ and inference/ deliberately remain separate: prompt formatting does not depend on PyTorch, while inference imports the sibling encoding module with an explicit Python path. No symlinks are required.

The tokenizer files are regular files so that the repository can be uploaded to Hugging Face without relying on local filesystem symlinks. The large model shards are described by model.safetensors.index.json and are not duplicated inside the source checkout used to assemble this repository.

Prompt encoding

See encoding/README.md. Both OpenAI-style JSON content blocks and the compact path TXT notation are supported. The two examples under inference/examples/ encode to identical prompts and token IDs.

Minimal inference

See inference/README.md for dependency installation, checkpoint conversion, and TXT/JSON inference commands.

License

This repository is licensed under the MIT License.

From the published model card. Full card on the HuggingFace links in the sidebar.

Using it via the API

Call it like any OpenAI endpoint

Once AxForge deploys unsloth-deepseek-flash-vision-exp for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (unsloth-deepseek-flash-vision-exp below is illustrative; you get the exact model name on deployment.)

$ curl -sS https://api.axforge.ai/v1/chat/completions \
  -H "Authorization: Bearer $AXFORGE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"unsloth-deepseek-flash-vision-exp","messages":[{"role":"user","content":"Hello"}]}'

Create an account — your API key is available in the console. 5M tokens/month currently included with every new account at launch.

© 2026 AxForge · EU-hosted AI infrastructure Pricing Docs Trust Privacy Terms