DeepSeek V4 Pro

LLM Provider / Model · Complex reasoning, agentic coding, hard debugging with long context

At a glance

Input price	$0.44
Output price	$0.87
Cache price	$0.015
Price tier	Mid
Context window	1M+
Max output	384K
Context tier	500K+
Speed tier	Slow/Reasoning
Latency	medium
Knowledge cutoff	Jun 2025
Modality	Text-only
Model ID	deepseek-v4-pro
Provider	DeepSeek
HumanEval	95%
MMLU	88%
SWE-Bench	62%
Benchmark	top-tier reasoning
Released	2026
Hosting	Closed/API
Capabilities	Tool use, Streaming, Structured output, Thinking mode, Deep reasoning

Tool use, Streaming, Structured output, Thinking mode, Deep reasoning

Complex reasoning, agentic coding, hard debugging with long context

Google Antigravity is built around Gemini 3 Pro; Claude and recent GPT-5 models also work, but DeepSeek V4 Pro is not in the supported model list.
Kiro's spec mode is tuned for Claude models — DeepSeek V4 Pro may work but spec-driven flows are best with Claude.
OpenAI Codex (VS Code) is tied to OpenAI's GPT-5.1 Codex family — DeepSeek V4 Pro is not selectable inside this integration.
Gemini CLI is locked to Google Gemini models — your LLM is DeepSeek V4 Pro.
Claude Code only works with Claude models — your LLM is DeepSeek V4 Pro.
Devin uses Cognition's proprietary model internally — your selected DeepSeek V4 Pro will be ignored.
OpenAI Codex (Cloud) runs GPT-5.1 Codex internally — your selected DeepSeek V4 Pro will be ignored.
Jules runs Gemini models internally — your selected DeepSeek V4 Pro will be ignored.
The Claude Code SDK is tuned for Claude models — DeepSeek V4 Pro may work via the model adapter but loses Claude-specific features (thinking, prompt caching, sub-agents).
Lovable uses a fixed internal model — your selected DeepSeek V4 Pro will be ignored.
Replit Agent 3 uses its own model selection internally — your selected DeepSeek V4 Pro will be ignored.

Build a full stack around DeepSeek V4 Pro — Flowpicker shows compatibility warnings before you commit.