DeepSeek Token Cost Calculator
Estimate DeepSeek API spend. Pick deepseek-flash or deepseek-v4-pro, enter monthly input and output tokens, cache hit %, and the share of traffic in peak hours. Cost = input × hit% × hit rate + input × miss% × miss rate + output × output rate, blended across peak and off-peak (half price). Estimates only; official DeepSeek pricing prevails.
Math runs in your browser. Nothing is uploaded.
Peak hours: 01:00–04:00 and 06:00–10:00 UTC, Monday–Friday, excluding Chinese public holidays. All other hours (weekends included) are off-peak at half price.
Custom $/1M rates (optional)
Monthly USD
—
Peak-hour spend
—
Off-peak spend
—
If 100% peak
—
If 100% off-peak
—
Search / Fetch spend
—
Estimates only; official vendor pricing prevails (2026-10-30). Cost = input × hit% × hit rate + input × (1 − hit%) × miss rate + output × output rate, blended by peak share. Search/Fetch: $0.75 per 1,000 successful requests (Harness / Claude Code / Codex tool calls billed from 2026-11-01 Beijing time).Official pricing: DeepSeek
LLM Prompt Caching Cost Calculator · OpenAI Token Cost Calculator · Claude Token Cost Calculator · Gemini Token Cost Calculator · Grok Token Cost Calculator
More in this group
- LLM Prompt Caching Cost Calculator No-cache vs cached prompt monthly cost and savings.
- OpenAI Token Cost Calculator GPT-5 / 4.1 / o-series token cost in USD.
- Claude Token Cost Calculator Fable / Haiku / Sonnet / Opus token cost in USD.
- Gemini Token Cost Calculator Gemini 2.5 / 3 Flash and Pro token cost in USD.
- Grok Token Cost Calculator Grok 4.7 / 4.6 / 4.3 token cost in USD.
- LLM API Cost Calculator Generic token cost from any $/1M rates.
How it works
- How is DeepSeek API cost calculated?
- Cost = input × hit% × hit rate + input × (1 − hit%) × miss rate + output × output rate, per 1M tokens, blended by peak share. Example: deepseek-flash, 100M input at 80% cache hit, 10M output, all peak → $0.48 + $6.00 + $12.00 = $18.48; all off-peak = $9.24.
- What are the current DeepSeek prices?
- Per 1M tokens (peak): deepseek-flash cache hit $0.006, miss $0.30, output $1.20; deepseek-v4-pro hit $0.044, miss $1.32, output $3.96. Off-peak is half: flash $0.003 / $0.15 / $0.60, pro $0.022 / $0.66 / $1.98.
- When are DeepSeek peak hours?
- 01:00–04:00 and 06:00–10:00 UTC, Monday to Friday, excluding Chinese public holidays. Everything else, including weekends and Chinese public holidays, is off-peak.
- Does DeepSeek charge for Search and Fetch?
- Yes: $0.75 per 1,000 successful Search or Fetch requests. Server-side tool calls through DeepSeek Harness, Claude Code, or Codex are free until per-request billing starts at 00:00 Beijing time on 2026-11-01.
- Are results billing-grade?
- No. DeepSeek may adjust prices; balance deductions follow the official page. Use this for planning only.