All AI models · LLM benchmarks · Methodology

DeepSeek

deepseek-ai/DeepSeek-V4-Pro

Flagship DeepSeek model for coding, reasoning, and agentic work

Model facts

Context window
1.05M tokens
Maximum output
393K tokens
Cheapest paid input
$1.74 per 1M tokens
Cheapest paid output
$3.48 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, temperature control, open weights, text.

Local hardware estimate

At 4K context: Q4_K_M 979.5 GiB, Q8_0 1724.1 GiB, F16 3120.0 GiB working memory.

Parameters
1598.8 billion
Architecture
deepseekv4
Model license
mit

Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.

Observed price history

  • 2026-08-24: $1.74 input / $3.48 output per 1M tokens

API providers

  • SiliconFlow (China) — model id deepseek-ai/DeepSeek-V4-Pro; $1.74 input / $3.48 output per 1M tokens; provider documentation