All AI models · LLM benchmarks · Methodology

DeepSeek

DeepSeek R1 (Turbo)

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Model facts

Context window
64K tokens
Maximum output
16K tokens
Cheapest paid input
$0.7 per 1M tokens
Cheapest paid output
$2.5 per 1M tokens
Open weights
yes
Providers
1

Capabilities and modalities

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

Observed price history

  • 2026-08-24: $0.7 input / $2.5 output per 1M tokens

API providers

  • NovitaAI — model id deepseek/deepseek-r1-turbo; $0.7 input / $2.5 output per 1M tokens; provider documentation