An experimental vision-capable DeepSeek V4 Flash model for low-cost multimodal reasoning and coding.
Get StartedRun /model and pick DeepSeek V4 Flash Vision · $0.14/M input · $0.28/M output
Key capabilities and pricing
Processes visual evidence alongside code and text.
Supports multiple reasoning-effort levels.
Low-cost input and output for iterative workflows.
Available in AdaL CLI and Desktop through the model selector
Use the coding environment where AdaL already understands your repo, tools, and task context.
Open the model selector and choose your model from the list.
Ask AdaL to inspect, plan, edit, test, and review with your chosen model powering the agent loop.
Open AdaL CLI or Desktop, run /model, and choose DeepSeek V4 Flash Vision.
Get Started with AdaL