deepseek-v4-pro · DeepSeek
DeepSeek's frontier tier at $1.32/$3.96 peak — 1M context, 384K output, thinking and non-thinking modes.
Last checked Aug 16, 2026. Calculations use the listed base rates; provider-specific tiers, cache writes, batch pricing, and long-context rules may differ. Note: Peak-hour rates; off-peak 50% off: $0.66/$1.98. Confirm the current rate at the official provider source.
Input
$1.32
per 1M tokens
Output
$3.96
per 1M tokens
Cached input
$0.044
per 1M tokens
Context window
1M
max output 384K
DeepSeek V4 Pro cost calculator
What DeepSeek V4 Pro costs per task
| Use case | Input tokens | Output tokens | Cost / request | Monthly @ 1K req/day |
|---|---|---|---|---|
| Customer support chatbot | 3,500 | 350 | $0.00288 | $86.394 |
| RAG / search-augmented answers | 8,000 | 500 | $0.007436 | $223.08 |
| AI coding assistant | 12,000 | 2,000 | $0.0146 | $437.184 |
| Document summarization | 25,000 | 600 | $0.0322 | $965.58 |
| Agentic workflow | 40,000 | 1,500 | $0.0256 | $766.92 |
| Content generation | 800 | 1,200 | $0.005502 | $165.053 |
| Data extraction & tagging | 2,000 | 250 | $0.00312 | $93.588 |
| Translation | 5,000 | 5,500 | $0.0274 | $822.69 |
Assumes each use case's typical cacheable share of input. See full cost scenarios.
Compare with alternatives
| Model | Input /M | Output /M | Context | Chat request* |
|---|---|---|---|---|
| DeepSeek V4 Pro | $1.32 | $3.96 | 1M | $0.005896 |
| GPT-5.6 Terracompare | $2.00 | $12.00 | 1.1M | $0.014 |
| Claude Sonnet 5 | $2.00 | $10.00 | 1M | $0.0124 |
| Mistral Large 3 | $0.50 | $1.50 | 131.1K | $0.0023 |
*4,000 in + 800 out tokens, 50% cached input where available.
Related calculations
FAQ
DeepSeek V4 Pro costs $1.32 per 1M input tokens and $3.96 per 1M output tokens, with cached input at $0.044 per 1M tokens. Verified Aug 16, 2026 against https://api-docs.deepseek.com/quick_start/pricing.
DeepSeek V4 Pro supports a 1,000,000-token context window with up to 384,000 output tokens per request, tokenized with DeepSeek BPE (V4).
At $1.32/M input and $3.96/M output, DeepSeek V4 Pro sits below GPT-5.6 Terra ($2.00/M in, $12.00/M out) — see the comparison table for full-workload differences.