DeepSeek V3.1 (Reasoning) Token Counter & Cost Calculator

Count tokens for DeepSeek V3.1 (Reasoning) and estimate the exact API cost — $0.59 per 1M input tokens, $1.69 per 1M output tokens — using a real o200k_base BPE tokenizer. Everything runs in your browser; nothing is uploaded.

0
tokens (o200k_base)
0
characters
0
words
$0
input cost
$0
output cost (est.)
$0
total per request

Counts are exact for OpenAI models (o200k_base is GPT-4o/4.1/5's tokenizer). For Claude, Gemini and other vendors — whose tokenizers are not public — treat the count as a close estimate (typically within ±15%).

Cost of this text across popular models

Close estimate (±15%): DeepSeek does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation.

Cost lookup — DeepSeek V3.1 (Reasoning)

TokensCost on DeepSeek V3.1 (Reasoning)
1K input tokens0.059¢
10K input tokens0.59¢
100K input tokens$0.0590
1M input tokens$0.5900
1K output tokens0.169¢
10K output tokens$0.0169

FAQ

How accurate is the DeepSeek V3.1 (Reasoning) token count?

Close estimate (±15%): DeepSeek does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation. Paste your own text above to see the exact number for your prompt.

How is DeepSeek V3.1 (Reasoning) API cost calculated?

Cost = (input tokens ÷ 1,000,000) × $0.59 + (output tokens ÷ 1,000,000) × $1.69 — DeepSeek V3.1 (Reasoning)'s official per-1M-token prices from Artificial Analysis.

See full DeepSeek V3.1 (Reasoning) pricing & benchmarks, or the main token counter for every model.