name = "deepseek-v4-pro"
description = "Flagship DeepSeek model for coding, reasoning, and agentic work"
family = "deepseek-thinking"
attachment = false
reasoning = true
reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["high", "max"] }]
tool_call = true
release_date = "2026-04-24"
last_updated = "2026-04-24"
open_weights = true

[limit]
context = 1048576
output = 1048576

[modalities]
input = ["text"]
output = ["text"]