All AI models · LLM benchmarks · Methodology

DeepSeek-V4-Pro-EL

Flagship DeepSeek model for coding, reasoning, and agentic work

Model facts

Context window
1M tokens
Maximum output
384K tokens
Cheapest paid input
$1.67 per 1M tokens
Cheapest paid output
$3.33 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

reasoning, tool calling, attachments, open weights, text.

Observed price history

  • 2026-08-24: $1.67 input / $3.33 output per 1M tokens

API providers

  • Poe — model id empiriolabs/deepseek-v4-pro-el; $1.67 input / $3.33 output per 1M tokens; provider documentation