DeepSeek V4 Pro pricing
DeepSeek V4 Pro costs $1.32 per million input tokens and $3.96 per million output tokens , with cached input at $0.044. Its context window is 1M tokens. Rates shown are peak; off-peak hours cost $0.66 in / $1.98 out.
Price per million tokens
| Input | $1.32 |
| Cached input | $0.044 |
| Output | $3.96 |
| Context window | 1M tokens |
| Batch discount | not offered |
Time-of-day pricing: 01:00-04:00 and 06:00-10:00 UTC are peak; all other hours bill at half
What it costs in practice
Monthly cost for three common workload shapes, with prompt caching applied.
| Workload | Shape | Per request | Per month |
|---|---|---|---|
| Support chatbot | 1.5k in / 400 out, 100k requests/month, 30% cached | $0.00299 | $298.98 |
| RAG / document Q&A | 12k in / 700 out, 50k requests/month, 60% cached | $0.00942 | $471.24 |
| Coding agent | 25k in / 2.5k out, 20k requests/month, 80% cached | $0.0174 | $347.60 |
Model your own workload with caching, batching and tokenizer correction →
Comparable models from other providers
| Model | Provider | Input | Output |
|---|---|---|---|
| GPT-5.1 | OpenAI | $1.25 | $10 |
| GPT-5 | OpenAI | $1.25 | $10 |
| Gemini 2.5 Pro | $1.25 | $10 | |
| Grok 4.3 | xAI | $1.25 | $2.5 |
All figures verified 2026-08-18 against DeepSeek's official pricing documentation . Fields the provider does not publish are shown as “—” rather than estimated.