All AI models · LLM benchmarks · Methodology

DeepSeek

DeepSeek V3.1 Thinking

DeepSeek chat model for instruction following, coding, and analysis

Model facts

Context window
128K tokens
Maximum output
66K tokens
Cheapest paid input
$0.2 per 1M tokens
Cheapest paid output
$0.7 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

tool calling, open weights, text.

Observed price history

  • 2026-08-24: $0.2 input / $0.7 output per 1M tokens

API providers

  • NanoGPT — model id deepseek-ai/DeepSeek-V3.1:thinking; $0.2 input / $0.7 output per 1M tokens; provider documentation