All AI models · LLM benchmarks · Methodology

DeepSeek

DeepSeek V4.1 Flash Beta

Fast DeepSeek model for efficient chat, coding help, and agent loops

Model facts

Context window
1M tokens
Maximum output
384K tokens
Cheapest paid input
$0.22 per 1M tokens
Cheapest paid output
$0.66 per 1M tokens
Open weights
no
Providers
1

Capabilities and modalities

reasoning, tool calling, attachments, text, image.

Observed price history

  • 2026-09-09: $0.22 input / $0.66 output per 1M tokens

API providers

  • Vercel AI Gateway — model id deepseek/deepseek-v4.1-flash-beta; $0.22 input / $0.66 output per 1M tokens; provider documentation