An ultra-affordable thinking model from DeepSeek. Use deepseek-v4-flash in AdaL for budget-friendly coding with reasoning.
Get StartedRun /model and pick DeepSeek V4 Flash · $0.14/M input · $0.28/M output
Key capabilities and pricing
One of the cheapest thinking models available anywhere.
Reasoning capabilities at near-zero cost.
Code generation and debugging.
Near-1M context at budget pricing.
Maximum value per token.
Rock-bottom pricing with reasoning.
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.
Key details about DeepSeek V4 Flash
"DeepSeek V4 Flash is incredibly cheap with near-1M context — great for budget work."
AdaL
"At $0.14/M input, among the cheapest thinking models available."
Pricing
"984K input tokens at this price is remarkable value."
Context
"Available now in AdaL CLI and Desktop."
Availability
Open AdaL CLI or Desktop, run /model, and choose DeepSeek V4 Flash.
Get Started with AdaL